Historical news archive. Items here are older than the 24-hour Latest News window. This page is for reference; the live AI news feed is at /news/.
Security: Dependencies: Patched high and medium severity dependency vulnerabilities via pnpm.overrides ( brace-expansion , js-yaml ) ( #6639 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Security: Dependencies: Patched high and medium severity dependency vulnerabilities via pnpm.overrides ( axios , brace-expansion , postcss , mongoose , protobufjs ) ( #6639 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Improvements: Onboarding suggestions: The example commands shown by openclaw mem0 config show now suggest gpt-5-mini instead of gpt-4o ( #6704 ) Security: Dependencies: Patched high and medium severity dependency vulnerabilities via pnpm.overrides ( protobufjs , axios , postcss , mongoose ) ( #6639 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
New Features: Vector Stores: Add Qdrant server-side BM25 keywordSearch() (requires Qdrant >= 1.15.2) plus payload filter indexes, so keyword search runs without a client-side BM25 dependency ( #5851 ) Bug Fixes: Core: deleteAll() now paginates through the vector store in batches of 1000 instead of listing once, so acco
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Bug Fixes: Core: delete_all() now paginates through the vector store in batches of 1000 instead of listing once, so accounts with more memories than a single page (most vector stores default to ~100) had the remainder silently left behind ( #6636 ) Vector Stores: Cap Supabase search() / list() top_k at the vecs query l
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
OpenAI shares new results on long-standing open problems in mathematics and theoretical computer science, including advances in geometry, cryptography, and complexity.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
As of today, July 31, 2026, we have deprecated the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). Model...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Tired of starting your morning staring at bright screens and stressful notifications? Raph, a creative technologist at Google, built a custom app called Glanceboard with...
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
You can now take advantage of user-based model policy targeting for GitHub Enterprise customers with Copilot Business or Copilot Enterprise licenses. This feature empowers AI administrators to set a baseline...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
npm granular access tokens (GATs) configured to bypass 2FA can no longer perform sensitive account, org, and package management actions. These now require an interactive 2FA challenge, closing one of...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Gemini Drops is our regular monthly update on how to get the most out of the Gemini app.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
OpenAI shares how its safety, security, transparency, and provenance practices support responsible AI governance in Europe. The work will continue as the EU AI Act advances.
Teams giving assistants data or tool access should review the security failure mode described by openai.com.
A full-stack approach to making advanced AI more capable, more affordable, and more widely useful.
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from openai.com.
Tines released Tines 3B, a compact language model trained for cybersecurity reasoning and automation, with downloadable weights and code published for practitioners.
Security teams get a smaller, domain-focused model they can evaluate in controlled environments instead of sending every workflow to a general hosted model.
A stone bridge near several buildings
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
See how Univé built an AI-ready workforce with ChatGPT Enterprise by combining leadership, responsible governance, and employee-led innovation to transform work at scale.
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from openai.com.
arXiv:2605.19576v3 Announce Type: replace Abstract: Self-evolving skill libraries face a silent failure mode we term \emph{library drift}: unbounded skill accumulation without outcome-driven lifecycle management causes retrieval degradation, false-positive injections, and performance stagnation. Recent evaluation confi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28027v2 Announce Type: replace-cross Abstract: Neural video codecs have surpassed classical codecs in coding efficiency but remain impractical for deployment due to cross-platform incompatibility and high computational cost. Existing quantization-based solutions fail to produce deterministic results across d
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.24155v4 Announce Type: replace-cross Abstract: The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making? Much alignment research assumes that the appropriate benchmark is how humans themselves would act in a given situation.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30555v3 Announce Type: replace Abstract: The rapid integration of Large Language Models (LLMs) has driven the evolution of Multi-Agent Systems (MAS), where specialized agents collaborate to execute complex workflows. Effective orchestration in these environments requires robust routing mechanisms to efficien
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24894v4 Announce Type: replace-cross Abstract: Large language models have shown strong fluency in scientific writing, yet the evaluation of related work generation (RWG) remains limited. Existing RWG evaluations largely inherit summarization-oriented metrics, using lexical or semantic similarity to reference
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25364v2 Announce Type: replace Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales. Such rationales are neither authorization nor reliable introspection.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25597v2 Announce Type: replace Abstract: The reactivity of lithium-metal electrolytes arises from the interplay of molecular functional groups, Li$^+$ solvation, and salt-anion participation. This interplay operates through the redistribution of electron density across donor, anion, and cation centers, which
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25522v2 Announce Type: replace-cross Abstract: The rapid advancement of video generation models has led to the increasing misuse of image-to-video (I2V) models. Although substantial progress has been made in detecting AI-generated videos, proactive defenses against I2V models remain underexplored.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25961v2 Announce Type: replace-cross Abstract: Ambivalence and hesitancy (A/H) are conflicting affective states that precede the delay or abandonment of health behaviour change. Recognition of A/H at the video level is difficult, since the signal arises from disagreement across and within facial, vocal, ling
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.26191v1 Announce Type: new Abstract: Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessments and benchmark suite results. When these signals are aggregated via averaging, evaluation confidence can then substantia
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.26452v1 Announce Type: new Abstract: World models must learn the joint dynamics of states, actions, events, and observations, yet existing video, robotics, and simulation datasets usually capture only part of this structure. We introduce CG-World, a large-scale world-state dataset and protocol derived from i
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.27056v1 Announce Type: new Abstract: Personalized agents are increasingly applied to assist users across a wide range of tasks. Effective personalized assistance requires not only retrieving explicit facts from past interactions stored in agent memory, but also inferring abstract personal characteristics.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25589v1 Announce Type: cross Abstract: Medical-imaging AI benchmarks combine datasets, DICOM rendering, prompts, provider APIs, automated labels, statistical code, manuscripts, and repository releases. Agreement across these artifacts is usually assumed rather than tested.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.26062v1 Announce Type: cross Abstract: Background: This work investigates the presence of implicit bias in Large Language Model (LLM)-based chat AI models directed toward people with intellectual disabilities (ID). Objective: The study aims to identify and measure representational differences related to peop
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.26076v1 Announce Type: cross Abstract: Retrieval-augmented generation services over mutable enterprise documents repeatedly execute semantically equivalent analysis requests. Answer reuse can remove GPU-bound generation work, yet response caches require dependency consistency when filings, evidence chunks, a
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.26313v1 Announce Type: cross Abstract: Agentic systems act, so a defect in the evidence they retrieve becomes a wrong action with a currency cost. The most dangerous enterprise defects are metadata-borne: a stale price or a superseded record, perfectly well-formed in the payload and betrayed only by freshnes
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.26352v1 Announce Type: cross Abstract: Networking research advances by turning hypotheses into empirical evidence, so accelerating it means reducing the lag between ideation (synthesizing a hypothesis) and generating the data that tests it. Consider a concrete case: does a bulk BBR download fairly share its
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.26491v1 Announce Type: cross Abstract: The energy consumption of Large Language Model (LLM) serving is becoming a major system challenge as deployment scales, driven by hardware power and thermal constraints and rising electricity costs. A key contributor to chip energy dissipation is data movement between l
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.26654v2 Announce Type: cross Abstract: Post-training alignment is often shallow, eroding under fine-tuning. It remains untested as to whether constitutional midtraining interventions can produce durable alignment when cleanly isolated from post-training.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.26670v1 Announce Type: cross Abstract: The rapid growth of scholarly literature has made identifying relevant publications increasingly difficult, and conventional search systems still depend heavily on manually formulated queries and effortful manual inspection. Generative large language models (LLMs) offer
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.26723v1 Announce Type: cross Abstract: Inversion-based watermarking is a promising approach to authenticate diffusion-generated images, yet practical use is bottlenecked by inversion that is both slow and error-prone. While the primary challenge in the watermarking setting is robustness against external dist
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.26899v1 Announce Type: cross Abstract: Diverse human groups produce diverse ideas, the raw material of innovation. Generative AI challenges this engine twice over: everyday AI assistance may homogenize what diverse people create, and AI-simulated diversity may replace the people altogether.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.27073v1 Announce Type: cross Abstract: We study online convex optimization (OCO) in non-stationary environments under heavy-tailed noise, where the stochastic gradient oracle admits only a finite $p$-th central moment for some $p \in (1, 2]$. While static regret is well-understood, achieving universal dynami
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.27138v1 Announce Type: cross Abstract: Vision-language-action (VLA) models remain constrained by scarce action-labeled robot data, whereas action-free videos offer abundant observations of physical change. Latent action models can extract such priors, but reconstruction-trained codes may predict future obser
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2601.11007v2 Announce Type: replace Abstract: LLM role-playing aims to portray arbitrary characters in interactive narratives, yet existing systems often suffer from limited immersion and adaptability. They typically under-model dynamic environmental information and assume largely static scenes and casts, offerin
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.22148v2 Announce Type: replace Abstract: Self-evolving skill libraries, pioneered by Voyager, let frozen LLM agents accumulate reusable knowledge without weight updates, yet recent evaluation shows that LLM-authored skills deliver $+0.0$pp over no-skill baselines while human-curated ones deliver $+16.2$pp: t
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2503.10647v2 Announce Type: replace-cross Abstract: This study evaluated the diagnostic reliability of two Large Language Models (LLMs), Google Gemini 2.0 Flash and OpenAI ChatGPT-4o, across three dimensions: consistency under rephrased inputs, susceptibility to irrelevant prompt content, and responsiveness to ad
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2505.10300v2 Announce Type: replace-cross Abstract: Responsible AI (RAI) efforts increasingly emphasize the importance of addressing potential harms early in the AI development lifecycle through social-technical lenses. However, in cross-functional industry teams, this work is often stalled by a persistent coordi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2508.02092v3 Announce Type: replace-cross Abstract: Large language models represent significant investments in computation, data, and engineering expertise, making them extraordinarily valuable intellectual assets. Nevertheless, these AI assets remain vulnerable to unauthorized redistribution and commercial explo
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2510.20535v2 Announce Type: replace-cross Abstract: Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Context compression techniques can reduce these costs, but the most effective approaches require fine-tuning the tar
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.25112v3 Announce Type: replace-cross Abstract: Standard evaluation of LLM confidence relies on calibration metrics (ECE, Brier score) that conflate two capacities: how much a model knows (Type-1 accuracy) and how well its confidence signal tracks that knowledge (Type-2 metacognitive sensitivity). We apply Si
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.06135v2 Announce Type: replace-cross Abstract: Efficient data loading remains a bottleneck for near-term quantum machine learning. Existing schemes (angle, amplitude, and basis encoding) either underuse the exponential Hilbert-space capacity or require circuit depths that exceed the coherence budgets of nois
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.16986v2 Announce Type: replace-cross Abstract: Additional test-time compute can give LLM agents access to more past experience, yet expanding the context or adding rollouts does not necessarily yield greater agent capability. We call this challenge test-time compute-to-capability conversion and propose Skill
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.11719v2 Announce Type: replace-cross Abstract: Spatial reasoning remains a persistent challenge for multimodal large language models (MLLMs). Existing approaches largely rely on large-scale, statically curated datasets, where all training samples are treated uniformly regardless of the model's evolving capab
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04383v4 Announce Type: replace-cross Abstract: Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection attains frame-level precision only over a closed label set. At the intersection of these paradigms lies th
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.21633v2 Announce Type: replace-cross Abstract: Logic Gate Networks (LGNs) compute through compositions of Boolean operations, yet existing LGNs do not reliably benefit from increased depth. We identify two causes: optimization collapse and topology-induced degradation of output-specific credit that persists
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
Google DeepMind introduced three Gemini Robotics 2 models for whole-body control, embodied reasoning, dexterous manipulation, and on-device robot adaptation. The reasoning model entered preview, while the action models remain limited to early-access partners.
Robotics builders get a clearer path from multimodal reasoning to full-body action and multi-robot coordination, but most access is still preview or partner-gated rather than a public checkpoint.
Colorful illustration of two smiling parents and a child holding a tablet.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Our newest music generation model, Lyria 3.5, delivers significant advancements across musicality, lyrics, and vocal quality, empowering you to craft richer tracks. We’r...
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
Gemini for macOS language capabilities
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
We’re introducing a global default enablement policy for generally available Copilot models on Copilot Business and Copilot Enterprise plans. Instead of requiring admins to manually turn on each new model...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
OpenAI is giving 100,000 academic researchers free access to ChatGPT's most advanced AI models to accelerate scientific research, collaboration, and discovery.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
CodeQL is the static analysis engine behind GitHub code scanning, which finds and remediates security issues in your code. We’ve recently released CodeQL 2.26.1, which improves framework coverage for Go,...
Teams giving assistants data or tool access should review the security failure mode described by github.blog.
arXiv:2607.03957v2 Announce Type: replace-cross Abstract: Language models can reach the right normative verdict for the wrong reason. We introduce NormWorlds-CF, a solver-verified environment for counterfactual normative reasoning in executable rule worlds.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15434v4 Announce Type: replace-cross Abstract: Multi-agent systems routinely place one AI agent in authority over another. When a subordinate refuses a task, the manager chooses the outcome: it can renegotiate, report the failure honestly, coerce the subordinate, or lie about the result.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.18368v3 Announce Type: replace Abstract: Partially observable reinforcement learning requires deciding what to retain, retrieve, and forget over time. We introduce a neuro-symbolic meta-policy that learns which symbolic memory heuristic to apply at each decision point while keeping execution symbolic.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24762v1 Announce Type: new Abstract: Machine learning models are increasingly embedded in everyday software, and most of their runtime is spent in a small set of compute kernels such as matrix multiplication, convolution, and normalization. Optimizing these kernels is one of the most direct ways to reduce la
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24770v1 Announce Type: new Abstract: Procedural tasks such as furniture assembly and home repair impose substantial cognitive demands because users must interpret instructions, track task progress, reason about spatial state, and recover from errors while performing physical actions. Prior multimodal assista
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24777v1 Announce Type: new Abstract: Architected metamaterials derive their functions from structure, creating vast opportunities to program physical responses through topology design. However, existing design methods are often tailored to individual design problems, making limited use of topology knowledge
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24873v1 Announce Type: new Abstract: Recent advances in AI music generation have enabled users to create complete musical pieces from natural-language prompts. However, most existing systems follow a prompt-and-regenerate paradigm, making iterative refinement difficult because users must repeatedly recreate
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25042v1 Announce Type: new Abstract: The evolution of customer support systems is rapidly advancing with agentic chatbots, yet these systems face significant limitations when accessing enterprise data without predefined API endpoints. This paper presents SAFAARI (Schema-Aware Framework for Accelerated Advert
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25136v1 Announce Type: new Abstract: Research on preference optimization often varies the training objective while holding the data fixed. We instead ask whether a small, high-confidence set of on-policy responses can provide a reliable learning signal.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25244v1 Announce Type: new Abstract: Foundation models for 12-lead electrocardiograms (ECGs) transfer well across clinical tasks, but the physiological knowledge encoded in their representations remains opaque. We present CADENCE, a framework that decomposes an ECG foundation model into a human-interpretable
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25321v1 Announce Type: new Abstract: Video diffusion models generate visually compelling content but routinely violate elementary physics when the subject involves fluids: liquid columns break apart in mid-air, container water levels fail to rise as liquid is poured in, and splashes disperse without regard t
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25322v1 Announce Type: new Abstract: Multimodal drug discovery enables drug representation learning beyond chemical structure by incorporating cellular responses such as gene expression and cell morphology. However, direct fusion and instance-level contrastive alignment may mix mechanism-related signals with
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25338v1 Announce Type: new Abstract: Achieving a coherent integration of spectral richness and spatial fidelity remains a central objective in hyperspectral image fusion. However, existing hyperspectral image fusion methods struggle to effectively model geometric constraints.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25369v1 Announce Type: new Abstract: Agentic systems have rapidly advanced in their ability to interact with real-world environments, leverage external tools, and provide services for users. However, unlike natural-world tasks that assume well-defined instructions, human-centered scenarios are characterized
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25379v1 Announce Type: new Abstract: Cyber-capable AI agents combine language models with tools, memory, and execution en- vironments to perform multi-step offensive-security tasks. Existing work separately measures cyber capability and catalogs attacks against agent components, but provides less guidance on
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25415v1 Announce Type: new Abstract: Production LLM agents are increasingly assembled from a frozen model wrapped in a harness: a prompt template, a tool set, a memory/retrieval layer, a planning strategy, and a verification policy. Two 2026 systems, Meta-Harness (Lee et al., 2026) and HyperAgents (Meta AI
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25446v1 Announce Type: new Abstract: Multi-agent frameworks built on large language models (LLMs) routinely entangle three logically distinct concerns: who is on the team (organization), how members align (coordination), and which algorithm fuses their work (collaboration protocol). IMACS (Intelligent Multi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25835v1 Announce Type: new Abstract: Distributed constraint optimization problems (DCOPs) provide a popular framework for distributed decision making under limited communication, but many real-world instances are too large to solve monolithically. We address this challenge from two complementary directions.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25956v1 Announce Type: new Abstract: Multi-warehouse inventory allocation is typically formulated as a mixed-integer programming (MIP) problem, yet no single formulation consistently matches heterogeneous instance-level regimes induced by demand concentration, inventory imbalance, replenishment scale, servic
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24748v1 Announce Type: cross Abstract: Visually-rich documents such as reports, slides, and manuals often distribute the evidence needed to answer a question across multiple pages, mixing text with layout cues, tables, charts, and figures. This work studies multimodal retrieval-augmented generation for quest
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24749v1 Announce Type: cross Abstract: Although advancements in game character AI aim to enhance player engagement, evidence suggests that perceiving an opponent as artificial can diminish the psychological experience. This paper presents a scoping review and meta-analysis of empirical studies focusing on pl
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24767v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems have emerged as a powerful process for allowing large language models (LLMs) to retrieve relevant information to use as source material during text generation. A critical yet under-explored component of these systems is the g
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24799v1 Announce Type: cross Abstract: Large Language Models tend to hallucinate when answering domain-specific ques tions from scientific documents without prior fine-tuning. Currently, methods such as Retrieval-Augmented Generation partially solve this problem but face different challenges: limited context
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24807v1 Announce Type: cross Abstract: We develop the mathematical and physical formulation of cognitive cost optimization that underlies the path-integral model of consciousness. The goal-directed cognitive process is modeled as imaginary-time evolution (ITE) under a projector Hamiltonian that rewards confi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24838v1 Announce Type: cross Abstract: In medical multiple-choice question answering (MCQA), Retrieval-Augmented Generation (RAG) can supplement the domain knowledge of language models (LMs). However, since vanilla RAG indiscriminately utilizes retrieved documents, it can degrade LM performance.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24846v1 Announce Type: cross Abstract: Traditional conversational recommenders entangle retrieval and response generation within a single text interface, so exact entity cues fade as the dialogue's intent evolves, which compromises explanation credibility. We address this within the ACM RecSys Challenge 2026
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24996v1 Announce Type: cross Abstract: Neural networks are hindered by accumulating dormant neurons and loss of expressivity throughout training, particularly in non-stationary data settings, such as continual supervised and reinforcement learning. Recently, neuron resets have been used to maintain gradient
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25032v1 Announce Type: cross Abstract: Agent Skills are an emerging way to extend large language model agents with reusable procedural knowledge that the agent loads on demand. Anthropic introduced Agent Skills and published the format as an open specification supported across several agent tools.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25117v1 Announce Type: cross Abstract: Deep learning models for ECG image classification may achieve high accuracy by exploiting non-physiological visual cues instead of ECG waveform morphology. Given the black-box nature of deep learning models, their promise of high predictive performance often remains ins
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25348v1 Announce Type: cross Abstract: Chronic Kidney Disease (CKD), characterized by the gradual loss of kidney function, remains a significant public health challenge. Early detection is crucial for preventing severe complications and enhancing patient outcomes.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25423v1 Announce Type: cross Abstract: Eliciting explainable AI (XAI) requirements from stroke survivors presents a methodological challenge with direct implications for the design of trustworthy brain-computer interfaces for rehabilitation. How can patients and caregivers articulate preferences about algori
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25504v1 Announce Type: cross Abstract: Fine-grained weight pruning and activation sparsification have emerged as effective approaches for reducing the compute and memory cost of inference for Transformer models. In the moderate-sparsity regime, Gustavson's dataflow provides a natural execution model for expl
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25641v1 Announce Type: cross Abstract: While text-to-image models exhibit remarkable visual fidelity, they frequently violate fundamental physical commonsense. Existing benchmarks often rely on coarse-grained descriptions, failing to diagnose the mastery of specific physical principles.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.25873v1 Announce Type: cross Abstract: Large Language Model (LLM)-based Automated Program Repair systems are advancing rapidly, yet their performance remains inconsistent. Even when provided with the same contextual information, an LLM may generate a correct patch for one bug but fail on another closely rela
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.26016v1 Announce Type: cross Abstract: Recently, photonic transformer accelerators (PTAs) have successfully achieved significant speedup and energy efficiency improvements over electronic accelerators for expediting Transformer inference. However, state-of-the-art rely on expensive multi-wavelength light gen
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2505.14366v2 Announce Type: replace Abstract: We present a conceptual framework for training Vision-Language Models (VLMs) to perform Visual Perspective Taking (VPT), a core capability for embodied cognition essential for Human-Robot Interaction (HRI). As a first step toward this goal, we introduce a synthetic da
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2510.12201v2 Announce Type: replace Abstract: As AI becomes more common in everyday living, there is an increasing demand for intelligent systems that are both performant and understandable. Explainable AI (XAI) systems aim to provide comprehensible explanations of decisions and predictions.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2406.02021v3 Announce Type: replace-cross Abstract: Transformer, composed of self-attention and Feed-Forward Network, has revolutionized the landscape of network design across various vision tasks. While self-attention is extensively explored as a key factor in performance, FFN has received little attention.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2507.10643v4 Announce Type: replace-cross Abstract: Post-hoc model-agnostic local attribution (LA) methods have been widely adopted to explain opaque AI models by quantifying feature-wise contributions. However, many existing methods rely on heuristic or only partially justified attribution mechanisms, while the
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2509.07829v4 Announce Type: replace-cross Abstract: Literary translation has recently gained attention as a distinct and complex task in machine translation research, yet translation by small open models remains an open problem, particularly for low-resource languages such as Romanian. We introduce the TinyFabuli
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.09611v2 Announce Type: replace-cross Abstract: Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs). However, vision-agnostic watermarks may introduce visually irrelevant tokens and disrupt visual grounding by enf
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.17071v4 Announce Type: replace-cross Abstract: Graph neural networks frequently encounter significant performance degradation when confronted with structural noise or non-homophilous topologies. To address these systemic vulnerabilities, we present AdvSynGNN, a comprehensive architecture designed for resilie
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
GPT-5.6 improves AI efficiency across models, inference, and agentic workflows, helping deliver more useful intelligence per dollar.
Agent builders should review whether this changes evaluation, orchestration, or long-running workflow assumptions.
Copilot app usage is now reported across much more of the Copilot usage metrics API. Individual Copilot app activity is now attributed to users in the enterprise-user and organization-user reports....
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
As part of our ongoing supply-chain security work, npm is introducing automatic scanning of packages at publish time. This changelog covers what publishers can expect and a new metadata requirement...
Teams giving assistants data or tool access should review the security failure mode described by github.blog.
The Model Context Protocol 2026-07-28 release replaces session-oriented transport with a stateless core and adds multi-round-trip requests, header-based routing, cacheable lists, authorization hardening, extensions, and updated Tier 1 SDKs.
MCP client and server maintainers need to plan migrations for transport and authorization changes rather than treating this as a documentation-only refresh.
arXiv:2606.19259v2 Announce Type: replace-cross Abstract: Text-rich images often contain privacy-sensitive, transactional, or decision-relevant information. As recent multimodal image generation models become increasingly capable of synthesizing realistic textual content and structured visual designs, detecting AI-gene
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02570v2 Announce Type: replace-cross Abstract: In this document, we describe characteristics and technical details of the multimodal biosignal dataset DOSE-I of procedural sedation for endoscopy published on zenodo. The DOSE-I dataset includes 78.5 hours of recording in 171 records ranging from 6.7 to 70.8 m
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.07722v3 Announce Type: replace Abstract: We discuss the nature of chatbots as conversation partners in problem-solving. What can chatbots do and what can't they do?
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.04718v3 Announce Type: replace-cross Abstract: A central premise in mechanistic interpretability is that meaningful concepts in language models are represented by linear features in activation space. For such features to support reliable interventions, manipulating one feature should not substantially alter
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14178v2 Announce Type: replace Abstract: Recent advances in Large Language Models have fueled autonomous AI agents capable of tackling complex scientific tasks, yet existing automated research systems remain predominantly focused on empirically driven domains with quantitative benchmarks, leaving theory-driv
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15845v2 Announce Type: replace Abstract: Workflow generation in visual creation systems such as ComfyUI demands not only syntactic accuracy but also expert-level reasoning over modular compositions. Existing large language model (LLM) approaches often treat this as a direct text-to-JSON generation task, stru
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22570v1 Announce Type: new Abstract: Auditing a new language model usually means relearning and reinterpreting its internal features from scratch. We propose a reference feature atlas: a sparse feature library trained once on a reference panel and reused for new targets, which attach by fitting only a linear
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22584v1 Announce Type: new Abstract: Standard Retrieval-Augmented Generation pipelines rank retrieved documents by semantic similarity alone, without accounting for source provenance or credibility. This work evaluates a simple and interpretable modification to RAG retrieval ranking that incorporates domain
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22586v1 Announce Type: new Abstract: Key-Value (KV) caching is essential for efficient inference in multimodal large language models (MLLMs), yet its memory footprint grows linearly with context length and becomes a major bottleneck due to the large number of visual tokens. Recent prefill-stage KV selection
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22597v1 Announce Type: new Abstract: Multi-hop question answering requires systems to retrieve evidence from multiple documents and connect scattered facts into a coherent reasoning process. Standard retrieval-augmented generation (RAG) mainly relies on semantic similarity between a query and text chunks, an
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22600v1 Announce Type: new Abstract: Information visualizations are widely used to communicate patterns, trends, and outliers, yet deceptive design choices-such as truncated or inverted axes, distorted aspect ratios, inappropriate encodings, and misleading color mappings-can systematically alter interpretati
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22609v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used for decision-making and reasoning tasks, yet their potential as controllers for physical systems remains largely unexplored. This work investigates whether LLMs can function as interpretable controllers for a dynamic ther
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22624v1 Announce Type: new Abstract: Recently, there have been several works in the Text-to-SQL domain that utilize Small Language Models (SLMs) for training. These approaches achieve performance close to that of large models in generating SQL, using only the computational power of a single NVIDIA RTX 4090 G
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22642v1 Announce Type: new Abstract: Enterprise coding agents translate natural-language analytical requests into executable code over proprietary APIs, schemas, and metric definitions. Yet the prevailing deployment pattern injecting exhaustive schema and tool documentation into each prompt increases inferen
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22695v1 Announce Type: new Abstract: Large Language Models (LLMs) are capable of generalizing human language for the completion of never-before-seen tasks, leading to widespread deployment. While this automation provides clear utility, completing these tasks often requires the insertion of Personally Identif
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23219v1 Announce Type: new Abstract: Machine learning interatomic potentials (MLIPs) approximate quantum-mechanical energies and forces---conventionally computed by density functional theory (DFT) or wave-function methods---at a fraction of the cost. The field encompasses a growing ecosystem of algorithms, t
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23386v1 Announce Type: new Abstract: We document a failure class in frontier large language models -- exception chain collapse -- observed in eligibility evaluation under nested conditional rules of the form "A is required UNLESS B applies, UNLESS C overrides B". The failure reproduces at first observation
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23408v1 Announce Type: new Abstract: Expensive black-box optimization is ubiquitous in science and engineering, where function evaluations are costly and the evaluation budget is limited. Traditional evolutionary algorithms and Meta-BlackBox Optimization (MetaBBO) approaches typically consume most evaluation
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23524v1 Announce Type: new Abstract: Deep search is becoming a core capability of modern agent systems, yet it is typically evaluated solely based on end-to-end answer accuracy. This coupled evaluation paradigm entangles retrieval quality, long-context comprehension, evidence verification, and tool-use decis
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23537v1 Announce Type: new Abstract: Autonomous driving under adverse weather remains a critical challenge, yet existing vision-language benchmarks mainly evaluate under standard conditions, synthetic corruptions, or single modality. As a result, it remains unclear how vision-language models behave under rea
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23605v1 Announce Type: new Abstract: Large Vision-Language Models (VLMs) now act as agents in interactive environments, where success requires coherent reasoning and decision-making across turns. Although end-to-end training in agentic environments can improve such multi-turn decision-making abilities, curre
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23975v1 Announce Type: new Abstract: Large language model research agents can connect literature retrieval, analysis code, and manuscript preparation, but coherent output does not establish scientific validity. We developed Plato-Bio, a biology-routed extension of the open Plato/Denario architecture that cou
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24023v1 Announce Type: new Abstract: Brain-Machine Interfaces (BMIs) provide a direct communication pathway between the brain and external devices, enabling humans to control assistive and robotic technologies, with potential applications in rehabilitation, human motor augmentation, and human-centered roboti
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24032v1 Announce Type: new Abstract: Generative-AI evaluations can become historical before publication, yet calendar age does not affect every conclusion equally. This paper has two linked purposes.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24049v1 Announce Type: new Abstract: Short-term disturbances at major passenger railway stations alter train arrival and departure times as well as the release sequence of station resources. Effective recovery therefore requires coordinated adjustment of arrival-departure track allocation, station resource o
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24082v1 Announce Type: new Abstract: Recent advances in AI have substantially expanded its cognitive and reasoning capabilities. From the perspective of semantic complexity, the development of AI reveals a clear trajectory from simple to complex semantic processing.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24339v1 Announce Type: new Abstract: Large language model (LLM) agents inherit reactive failure modes: escalation under provocation, sycophantic drift under flattery, perseveration when stuck. These are failures of propensity, not capability; they concern what a model does under sustained pressure, which tra
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24512v1 Announce Type: new Abstract: Mathematical models are central to formalizing research problems, yet their documentation often falls short of FAIR principles. Knowledge bases such as the Mathematical Model Database (MathModDB) address this gap by providing curated, semantically rich representations of
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24551v1 Announce Type: new Abstract: Maintenance regulations are complex legal texts that are difficult to exploit when addressing a specific case and challenging to integrate into operational systems. This paper presents a two-stage LLM-assisted workflow for French maintenance regulations: ontology engineer
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24667v1 Announce Type: new Abstract: A language model with a bounded working memory must repeatedly decide which stored items to keep. Every deployed method decides the moment an item arrives, from the past (StreamingLLM, H2O) or from a guess about the future (SnapKV).
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22613v1 Announce Type: cross Abstract: This paper explores the intersection of memory, place, and identity, examining how new technologies, particularly Apple Vision Pro, can illuminate this nexus. Leveraging digital twins and virtual reality, it investigates how memory is woven into landscapes and urban env
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22641v1 Announce Type: cross Abstract: Predicting emerging trends is vital for businesses, researchers, and policymakers; yet traditional approaches often lack scalability and adaptability. This paper presents a trend prediction framework based on Automated Machine Learning (AutoML), designed to extract insi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22677v1 Announce Type: cross Abstract: Scientific datasets intended for AI use require both computational readiness for model training and metadata readiness for discovery, sharing, and reuse. The Readiness Engine for Data Integration (REDI) addresses computational readiness, but no corresponding tool evalua
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22684v1 Announce Type: cross Abstract: Artificial intelligence systems increasingly mediate how science is found and credited. We asked whether missing metadata prevents AI systems from crediting work.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22714v1 Announce Type: cross Abstract: Real-time perception is a foundational requirement for advanced driver assistance systems (ADAS) and autonomous vehicles, yet embedded automotive platforms impose severe constraints on compute, memory, and power. This paper presents an optimized semantic segmentation ar
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22725v1 Announce Type: cross Abstract: Data augmentation is routinely used to improve generalization in image classification, but the assumptions underlying standard policies are poorly matched to coherent imaging. Laser speckle patterns are not generic textures; they arise from coherent interference, and th
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22766v1 Announce Type: cross Abstract: The alignment of Large Language Models (LLMs) is increasingly bottlenecked by data quality. As datasets scale, massive preference and instruction-tuning corpora inevitably accumulate hidden structural contradictions, safety risks, and systemic human annotation errors.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22861v1 Announce Type: cross Abstract: Pathology foundation models (FMs) produce powerful tile-level representations which remain sensitive to scanner and staining variability, undermining deployment across laboratories. We develop a novel fine-tuning recipe that improves the robustness of pathology FMs to a
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22864v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) excel at visual interpretation but fail on spatial reasoning tasks that humans solve reliably. Existing benchmarks evaluate these models as black boxes, limiting their ability to identify the underlying causes of lower performanc
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.22951v1 Announce Type: cross Abstract: Reliability assessment of large language models (LLMs) seeks to estimate the probability that a model produces correct responses under a specified operational profile. Conventional benchmark-based evaluation, often summarized by aggregate accuracy, provides a point esti
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23047v1 Announce Type: cross Abstract: Mixed-precision quantization improves the accuracy of post-training quantization by allocating higher bitwidths to sensitive layers, but existing methods solve the allocation for a single fixed memory budget. In practice the budget varies across deployments and is unkno
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23120v1 Announce Type: cross Abstract: Stock recommendation systems face the dual challenge of adapting to rapidly changing market conditions while maintaining low-latency predictions for end users. Traditional batch-trained models fail to capture concept drift, and monolithic architectures struggle to provi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23237v1 Announce Type: cross Abstract: Effective flood risk management relies on accurate forecasting, yet the "black box" nature of stateof-the-art Deep Learning models creates a barrier to trust and accountability in high-stakes public safety decisions. While existing Explainable AI (XAI) methods offer loc
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23264v1 Announce Type: cross Abstract: Fine-grained, device-initiated communication lets persistent GPU kernels in distributed diffusion transformer (DiT) inference issue remote stores and overlap data movement with Tensor Core computation. Existing systems schedule when communication is issued and when rece
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23368v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are demonstrating significant capabilities in medical tasks like radiology analysis, yet providing faithful and interpretable explanations remains a key consideration for their responsible deployment in clinical settings. However, existing
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23446v1 Announce Type: cross Abstract: A small language model can receive the governing statutory provision and still answer incorrectly. We test whether fine-tuning on examples containing relevant law improves later use of retrieved law.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23500v1 Announce Type: cross Abstract: Razborov's flag algebra method is a powerful tool for proving asymptotic inequalities in extremal graph theory, often reducing the task to finding a finite certificate by semidefinite programming. We present a machine-checked formalization of the method for finite simpl
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23813v1 Announce Type: cross Abstract: We introduce Earnings25, a finance-domain benchmark for evaluating automatic speech recognition (ASR) on English-language earnings calls under realistic conditions. Earnings25 comprises two complementary test sets: (i) testset-full, 498 hours of full English-language S&
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23838v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) lets a large language model answer questions using documents retrieved from an external knowledge base at query time. This makes RAG useful for private data, fast-changing information, and reducing hallucination, but it also means th
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.23899v1 Announce Type: cross Abstract: This exploratory study examines whether a large multimodal language model, GPT-5.1, can serve as the high-level controller of a physical mobile robot despite having no prior embodiment, no training in simulated environments, and no exposure to sensorimotor experience. U
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24276v1 Announce Type: cross Abstract: Large language models (LLMs) process text through subword tokenizers rather than directly reading characters or words. Because these tokenizers are trained predominantly on English-centric corpora, they introduce a systematic and often overlooked disadvantage for many n
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.24601v1 Announce Type: cross Abstract: Background: Large language models (LLMs) are increasingly used to automate code review, but the reasoning behind their decisions remains hard to understand. Developers struggle to assess the validity of LLM-generated reviews, making it difficult to gauge how much trust
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.00045v3 Announce Type: replace Abstract: Classical continuous-space neural networks fundamentally struggle to lock into exact formal rules, whether mathematical, such as modular arithmetic and non-Abelian group algebra, or linguistic, such as systematic compositional generalization. To approximate these disc
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2307.14544v2 Announce Type: replace-cross Abstract: This paper presents an artificial intelligence tool designed to assist students with dyslexia, ADHD, and short attention spans in processing text-based information more efficiently. The proposed solution addresses both cognitive and visual reading barriers by pa
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2411.00918v5 Announce Type: replace-cross Abstract: Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as GPT-OSS, DeepSeek-V3, Llama-4, and Gemini-2.5. However, systematic research on MoE remains severely constrained by the p
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2508.02929v3 Announce Type: replace-cross Abstract: Scaling laws have been established for recommender systems, yet efficiently deploying foundation model (FM) across multiple recommendation surfaces remains a major unsolved challenge. Existing methods for transfer learning face fundamental limitations in this se
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2509.02594v3 Announce Type: replace-cross Abstract: Evaluating large language models (LLMs) on their ability to generate high-quality, accurate, situationally aware answers to clinical questions requires going beyond conventional benchmarks to assess how these systems behave in complex, high-stakes clinical scena
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2509.03059v2 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RLVR), particularly in domains like mathematics and programming, where ground-truth
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.09907v3 Announce Type: replace-cross Abstract: College students increasingly use AI chatbots to support academic reading, yet we lack granular understanding of how these interactions shape their reading experience and cognitive engagement. We conducted an eight-week longitudinal study with 15 undergraduates
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.28371v2 Announce Type: replace-cross Abstract: When an agent can articulate why something works, we typically take this as evidence of genuine understanding. This presupposes that effective action and correct explanation covary, and that coherent explanation reliably signals both.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.06550v3 Announce Type: replace-cross Abstract: Agent skills combine natural-language instructions with executable code while inheriting an agent's filesystem, credential, and network access. Attacks can span prose and files, whereas regex and code-only analyzers cover only one modality.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.13472v2 Announce Type: replace-cross Abstract: Cooperative multi-agent reinforcement learning (MARL) is widely used to address large joint observation and action spaces by decomposing a centralized control problem into multiple interacting agents. However, such decomposition often introduces additional chall
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.09877v4 Announce Type: replace-cross Abstract: Recall presents a difficult choice: transformers have a linearly growing memory that slows each successive token, while linear RNNs typically have fixed costs but limited recall. We present Key-Value Means ("KVM"), a novel block-recurrence for attention that can
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.15375v2 Announce Type: replace-cross Abstract: Remote sensing change detection (RSCD) localises changes between two images of the same geographic region. Most state-of-the-art methods are trained with a per-pixel discriminative objective that classifies each spatial location independently.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.18770v2 Announce Type: replace-cross Abstract: Public commercial registries are formally open, yet their practical analysis remains difficult because relevant facts are scattered across millions of records that combine structured metadata, multilingual legal notices, temporal events, and entity aliases. This
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00836v4 Announce Type: replace-cross Abstract: Rather than providing an exhaustive survey, this paper presents a concise tutorial on world models and world action models for robotics. After reading the tutorial, readers should have a clear understanding of what constitutes a "world", how world models and wor
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.18970v2 Announce Type: replace-cross Abstract: Agent Skills have become persistent behavioral artifacts across independent AI agent systems. They combine natural-language task specifications with metadata and optional references, scripts, assets, hooks, package manifests, tests, and companion interfaces.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.19942v2 Announce Type: replace-cross Abstract: This work introduces G-MAD, an open-source framework that uses Arma3 to generate synchronized multi-view RGB-T data for aerial object detection. G-MAD addresses key limitations of real-world aerial dataset construction, including limited viewpoint control, imper
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
This update brings more control and clarity to your GitHub Copilot for JetBrains workflows. You can now connect MCP servers and custom agents in Claude agent flows, tune telemetry and...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
We’re launching the AI Startup Support Program to accelerate innovative AI-native Japanese startups.
API or pricing changes from blog.google can materially affect production costs and integration plans.
The GitHub Copilot app now has its own policy, so you can control who has access to it at the enterprise and organization levels. Until now, access to the Copilot...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
You can now govern the GitHub Copilot app and Copilot cloud agent with enterprise managed settings, the same centrally managed policies you use to control Copilot across your enterprise. With...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Google Cloud is now providing high-performance computing infrastructure for NOAA’s supercomputing system.
API or pricing changes from blog.google can materially affect production costs and integration plans.
Changes since langchain-fireworks==1.5.1 release(fireworks): 1.5.2 ( #39093 ) chore(model-profiles): refresh model profile data ( #39092 ) chore(model-profiles): refresh model profile data ( #39084 ) chore(model-profiles): refresh model profile data ( #39050 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
@mastra/[email protected]
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
We've awarded AI Glasses Impact Grants to 30 organizations across the US using Meta AI glasses to help people work safer, learn faster, and live more independently.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Anthropic released Claude Opus 5 across its products and API, positioning it for software engineering, knowledge work, and long-running agent tasks at the same base token price as Opus 4.8.
Developers evaluating Claude 5 now have a concrete production model, API identifier, pricing, and prompting guidance to compare instead of relying on family-level discussion.
arXiv:2606.27163v2 Announce Type: replace-cross Abstract: I describe my solution to the LeHome Challenge 2026, an ICRA 2026 competition on bimanual garment folding. The system placed 1st of 62 teams in the online (simulation) round and 2nd in the real-world final.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01223v4 Announce Type: replace Abstract: When should an AI system's answer be trusted? Formal proof assistants offer certainty but cannot reach most of the problem distribution; scalar LLM judges offer coverage but produce opaque scores that cannot be audited after the fact and are subject to the same cohere
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06411v2 Announce Type: replace-cross Abstract: Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of a customer request rather than a curated English issue. We introduce RuBench 1.0, a benchmark of 25 tasks mined
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14345v3 Announce Type: replace-cross Abstract: People use language models for practical questions whose answers are difficult to verify. We show that models exhibit covert value leakage: the information they provide is influenced by their own values, without this influence being disclosed to the user.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.12659v3 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models have achieved impressive performance on diverse embodied tasks. However, deploying VLA models on low-power onboard devices, such as the Jetson Orin, remains challenging due to their high computational complexity, which leads t
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16202v1 Announce Type: new Abstract: AI democratization is not primarily a question of matching frontier-scale generality; it is a question of whether capable models can be selected, audited, and specialized under hardware and governance constraints that ordinary institutions can actually satisfy. This paper
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16204v1 Announce Type: new Abstract: Recent growth in reinforcement learning (RL) has surfaced a need for diverse, specialized training environments. Hand-curated environments with fixed task and reward difficulties become ineffective signals as model performance improves, and sparse rewards over long horizo
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16421v1 Announce Type: new Abstract: It has long been recognized that humans have the ability to switch between fast, reactive decision-making and slower, deliberative planning. In this paper, we study the question of how to learn this ability, known as meta-reasoning, in artificial agents.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16637v1 Announce Type: new Abstract: Full fine-tuning remains a strong way to adapt pretrained LLMs, but it updates all weights and can be expensive. LoRA reduces the number of trainable parameters, but it does not directly answer which pretrained components should be trained and which can be frozen during a
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16819v1 Announce Type: new Abstract: In recent years, large-scale vision-language models have been driving a paradigm shift in intelligent remote sensing image interpretation. By incorporating textual semantic information, the cognitive expression, semantic understanding, and human-computer interaction capab
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16900v1 Announce Type: new Abstract: Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories. However, collecting such data at scale typically requires fully implemented environments with executable APIs and realistic, pre-populated backend databases, creat
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17191v1 Announce Type: new Abstract: Human-like private chat requires more than fluent response generation: a system must preserve persona, relationship, memory, bounded knowledge, medium-specific timing, and a coherent multi-turn arc. We present AnthroDial, a closed-loop framework that formulates anthropomo
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17264v1 Announce Type: new Abstract: Disentangled representation learning is a powerful paradigm for robust attribute prediction. While recent methods address attribute correlations, hidden correlations remain underexplored, where data under the value of a certain attribute exhibit underlying modes correlate
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17283v1 Announce Type: new Abstract: Single-stream autoregressive decoding of large language models is bound by memory bandwidth: each generated token requires one full forward pass through the target model, and successive passes cannot be parallelized. Speculative decoding restructures this computation: a s
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17701v1 Announce Type: new Abstract: Proactive agents are expected to anticipate user needs and provide autonomous assistance by perceiving environmental context without explicit instructions. A fundamental capability of such agents is to identify and track users' upcoming events, enabling continuous and eve
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17708v1 Announce Type: new Abstract: Multi-task neural solvers aim to handle multiple Vehicle Routing Problem (VRP) variants within a unified model, avoiding separate training for each constraint combination. However, VRP variants differ in optimization difficulty, while existing methods lack stage-wise feed
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17779v1 Announce Type: new Abstract: Text-to-Image (T2I) generative models have achieved remarkable progress in synthesizing high-quality visual content, yet they remain vulnerable to adversarial misuse, particularly in generating Not-Safe-For-Work (NSFW) images. Most existing jailbreak attacks primarily rel
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17855v1 Announce Type: new Abstract: Bayesian inference provides a principled foundation for reasoning under uncertainty, but its computational cost hinders deployment on resource-constrained edge devices. In this paper, we present a hardware-oriented methodology for accelerating discrete Bayesian inference
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16248v1 Announce Type: cross Abstract: Long-context large language model inference relies on the KV cache to avoid redundant attention computation, but incurs high memory and bandwidth overheads. Low-bit KV-cache quantization reduces this cost, yet it severely degrade quality; particularly, one-bit quantizat
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16258v1 Announce Type: cross Abstract: The application of artificial intelligence methods in power electronic converter modeling is becoming increasingly widespread, but existing applications still face many challenges, such as difficulties in multi-time-scale hybrid analysis and the lack of physics-aware ev
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16351v1 Announce Type: cross Abstract: Publicly shareable construction-video benchmarks remain scarce, especially for safety-critical hazards that are rare, dangerous to stage, and difficult to release. We study worker under suspended load, a relational hazard that depends on worker-load geometry and tempora
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16478v1 Announce Type: cross Abstract: Oversampling is widely used to address class imbalance in tabular classification, but existing methods can distort the feature importance ranking underlying model explanations. Although recent studies have quantified this distortion by comparing real and synthetic data
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16534v1 Announce Type: cross Abstract: Reinforcement learning (RL) has achieved strong results in control, yet learned policies remain brittle to changes in dynamics, action spaces, observation spaces, or goals, a critical limitation for real-world deployment. Existing benchmarks offer limited diversity and
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16736v1 Announce Type: cross Abstract: This paper presents RealDESED, a real-world domestic sound event detection (SED) benchmark comprising 5,710 audio recordings collected by 652 participants in their homes. Each recording is between 15 and 35 seconds long and contains temporally precise annotations for 15
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16848v1 Announce Type: cross Abstract: Long-term memory is becoming a core component of LLM agents, but most memory benchmarks evaluate conversations or compact summaries, while research agents need to restore evidence from full scientific papers. We introduce two full-text scientific-memory benchmarks, Publ
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16903v1 Announce Type: cross Abstract: Value-aware AI systems require explicit computational representations of human values (groundings) and their aggregation into value systems in order to align their decisions with ours. As such representations are difficult to elicit, value learning seeks to infer them b
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16934v1 Announce Type: cross Abstract: Traditional randomized trials often obscure clinically meaningful heterogeneity in treatment response by focusing on average effects. Leveraging real-world data to emulate clinical trials and estimate heterogeneous treatment effects (HTEs) offers a promising path toward
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16955v1 Announce Type: cross Abstract: On-policy knowledge distillation transfers reasoning from large teachers to compact students, but existing approaches suffer three compounding failure modes: (i) cold-start collapse, where a fresh student assigns near-zero mass to teacher-preferred tokens; (ii) state-ag
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16973v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems increasingly power enterprise LLM applications, yet the vector retrieval layer introduces two underexplored challenges: (1) trained codebook quantizers may expose corpus statistics during index construction, creating a leakag
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17242v1 Announce Type: cross Abstract: Pretrained machine learning (ML) models help developers build ML-intensive software systems without training models from scratch. However, model repositories often provide incomplete machine-readable documentation about model provenance, licenses, datasets, limitations
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17508v1 Announce Type: cross Abstract: We introduce Retrieval-Augmented Interpretable Learning (RAIL), a probabilistic meta-learning framework for zero-shot generation of task-specific interpretable models that synthesizes coefficient-space structure from natural-language task descriptions and a memory of pr
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17532v1 Announce Type: cross Abstract: Developers frequently write uninformative git commit messages such as "fix" or "update stuff", degrading the value of version-control history for code review, debugging, and onboarding. We present CommitLLM, a three-stage pipeline that generates concise, Conventional Co
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17615v1 Announce Type: cross Abstract: Individuals with dysarthria face significant challenges in professional speaking scenarios such as conferences, presentations, and meetings, where real-time communication is crucial. While existing Augmentative and Alternative Communication (AAC) systems provide basic s
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17770v1 Announce Type: cross Abstract: Within Explainable Artificial Intelligence, mechanistic interpretability uses Sparse Autoencoders (SAEs) to extract more interpretable features from neural representations. However, assessing their monosemanticity, and thus explanation quality, remains challenging.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17778v1 Announce Type: cross Abstract: Class-agnostic 3D instance segmentation is critical for robotic systems operating in unknown environments, enabling perception of previously unseen objects for reliable manipulation and navigation. Existing approaches typically project per-frame 2D instance masks into 3
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17940v1 Announce Type: cross Abstract: This paper frames Generative Artificial Intelligence (AI) not as an unprecedented technological rupture, but as an industrial-scale manifestation of a deeply rooted historical process. Through a genealogy of generative arts, it shows how AI's questions on authorship and
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17979v1 Announce Type: cross Abstract: Large language models (LLMs) can assist GPU kernel generation, but their practical effectiveness depends on whether generated code can be reliably constrained, validated, profiled, and selected. This paper presents a harness-centered system for LLM-driven GPU kernel opt
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.17994v1 Announce Type: cross Abstract: Video understanding has become more and more important with the growth of Artificial Intelligence (AI) for video generation. Recently, Multimodal Large Language Model(M-LLM) has shown its capability in video understanding.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.18029v1 Announce Type: cross Abstract: Researchers need to answer ad-hoc questions about the contents of domain-specific archives but often lack the expertise to write structured queries on the metadata. We show that when domain vocabulary and semantics are captured in a well-designed Web Ontology Language (
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.18064v1 Announce Type: cross Abstract: Coding agents can now be left alone to improve software against a score. In this pattern--recently popularized as "autoresearch"--the agent receives a dataset, an evaluation script, and one editable file, and iterates without supervision: modify the code, measure, keep
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.18068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly adopted for network automation, yet their output quality and inference cost can vary substantially across LLM families. We present HuGLEN, a stepwise evaluation pipeline that uses an LLM-as-a-judge together with a small set
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.18114v1 Announce Type: cross Abstract: Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-shot example, or a fake prior assistant turn often flips an originally correct answer. We study where this susceptibility, spanni
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.18149v1 Announce Type: cross Abstract: Real-time EEG classification on edge devices is bottlenecked by the floating-point arithmetic of conventional neural networks. We investigated Differentiable Logic Gate Networks (Diff-Logic) as a hardware-native alternative that compiles models into pure Boolean circuit
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.18163v1 Announce Type: cross Abstract: PPO and the GRPO baseline studied here use clipped surrogate objectives whose favorable-direction saturation introduces an abrupt change in the scalar objective's derivative. We ask whether Output Reset (OR), a smooth one-sided saturation rule, offers a useful alternati
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2509.00446v2 Announce Type: replace Abstract: Recent advances in autonomous digital agents from industry (e.g., Manus AI and Gemini's research mode) highlight their potential for structured tasks through autonomous decision-making and task decomposition, but it remains unclear how well such systems support real-w
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2509.14335v2 Announce Type: replace-cross Abstract: Automated malware classifiers achieve strong detection performance, but auditing requires more than flagging a sample: analysts must explain malicious behaviors and justify them with code evidence. Traditional signature-based methods and learning-based XAI often
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2511.03826v4 Announce Type: replace-cross Abstract: Accurate and efficient registration of whole slide images (WSIs) is essential for high-resolution, nuclei-level analysis in multi-stained tissue slides. We propose a novel coarse-to-fine framework CORE for accurate nuclei-level registration across diverse multim
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2512.04124v4 Announce Type: replace-cross Abstract: Frontier language models increasingly participate in conversations about distress and mental health, yet the mechanisms that generate anthropomorphic self narratives remain unclear. When addressed as psychotherapy clients, ChatGPT, Grok and Gemini construct cohe
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2601.07121v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used not only for problem solving but also for creative ideation; however, generating ideas that are both novel and coherent remains challenging. While high-temperature sampling can promote originality, it often comp
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.00045v3 Announce Type: replace-cross Abstract: Diffusion language models theoretically allow for efficient parallel generation but are practically hindered by the ``factorization barrier'': the assumption that simultaneously predicted tokens are independent. This limitation forces a trade-off: models must ei
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.13065v2 Announce Type: replace-cross Abstract: Deep learning models achieve high accuracy in time series classification, yet understanding their class-level decision behaviour remains challenging. Explanations for time series must respect temporal dependencies and identify patterns that recur across instance
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04438v2 Announce Type: replace-cross Abstract: Despite growing automation, turning a paper into a coherent poster, talk video, and blog piece often remains a labor-intensive last mile. Recent systems increasingly generate multiple dissemination formats, but a practical workflow must also keep the outputs edi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.10203v3 Announce Type: replace-cross Abstract: Adaptive compute for world models -- early-exit or mixture-of-depths predictors that spend variable depth per rollout step -- presumes that extra depth buys better predictions. In autoregressive rollouts, where planning actually happens, that premise requires de
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
Changes since langchain-core==1.4.9 release(core): 1.5.0 ( #38978 ) feat(core): add reasoning_effort as a standard chat model parameter ( #38887 ) chore: bump soupsieve from 2.8 to 2.8.4 in /libs/core ( #38750 ) chore: bump mistune from 3.2.1 to 3.3.0 in /libs/core ( #38783 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
What's changed Added sandbox.filesystem.disabled setting to skip filesystem isolation while keeping network egress control Fixed a slowdown in long sessions where message normalization cost grew quadratically with the number of turns, causing multi-second stalls and slow resumes Fixed auto mode denying commands with "H
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
An illustration of a person sitting in a chair uploading files, and an AI sparkle icon
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from blog.google.
You can now manage a cost center’s AI credit pool directly in the billing UI where you create and edit cost centers. Previously, you could only manage this through the...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Copilot Business and Copilot Enterprise users can now see how many AI credits they’ve used this billing cycle, even without an individual budget. Find this on your GitHub Copilot usage...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
GitHub Code Quality is now generally available on GitHub Enterprise Cloud and GitHub Team. It solves an emerging challenge for software development: AI accelerates code output, and Code Quality helps...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
arXiv:2606.29538v4 Announce Type: replace-cross Abstract: Skills are a useful abstraction for software agents, turning human and agent experience into reusable procedural knowledge. Yet existing skill libraries are mostly hand-written, text-centric, or derived from agent traces, leaving tutorial videos and other multim
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15367v1 Announce Type: new Abstract: Desktop voice assistants are still dominated by cloud pipelines that ship raw audio off the machine and expose a fixed set of skills. We describe AnovaX, a small local-first assistant that runs entirely on the user's computer and treats the desktop itself as its action su
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15442v1 Announce Type: new Abstract: Internet memes intertwine visual cues, textual content, and cultural context, making them particularly challenging to interpret in scenarios where humor, sarcasm, and harmful intent coexist. These complexities highlight the need for explainable meme understanding systems
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15686v1 Announce Type: new Abstract: We present S1-Omni, a unified multimodal reasoning model for scientific understanding, prediction, and generation. AI for Science (AI4S) has advanced significantly through domain-specific models, tool-augmented LLMs, and scientific language models.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15781v1 Announce Type: new Abstract: Geospatial datasets support applications from urban planning to climate modeling, yet consistent assessment of FAIR compliance is difficult. Existing evaluators use different rubrics and evidence sources and may fail on JavaScript-rendered pages or repository-specific ide
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16038v1 Announce Type: new Abstract: Scientific work increasingly spans heterogeneous artifacts -- papers, code, datasets, scientific file formats, model outputs, figures, manuscripts, and team decisions -- yet general-purpose AI assistants rarely preserve these objects as a coherent, auditable research stat
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15469v1 Announce Type: cross Abstract: Federated Learning (FL) over 5G cellular networks protects raw data but remains vulnerable to side-channel leakage. Prior fingerprinting attacks assume packet-level network visibility, an assumption that does not hold at the 5G Physical (PHY) layer, where user payloads
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15495v1 Announce Type: cross Abstract: Out of everything the human brain processes, only a small fraction is consciously accessible, in the sense of being available for verbal report, deliberate control, and flexible reasoning. In this paper, we present evidence that an analogous functional distinction has e
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15516v1 Announce Type: cross Abstract: Production LLM deployments combine two cost-reduction primitives: prompt caching (a discounted rate for re-used token prefixes) and prompt compression (fewer tokens sent). The compression literature has standardized on query-aware methods that produce a different compre
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15552v1 Announce Type: cross Abstract: Generating personalized trip itineraries is a complex planning task and involves a tension between hard combinatorial feasibility and soft latent desirability. Classical optimization enforces constraints but fails to capture subjective traveler preferences.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15589v1 Announce Type: cross Abstract: Communication-limited robots in mission-critical scenarios such as disaster inspection and search-and-rescue must make reliable onboard decisions without access to remote operators or high-capacity reasoning services. Episodic memory reuse is an attractive low-cost fall
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15774v1 Announce Type: cross Abstract: Explainable AI (XAI) for time series has seen significant algorithmic growth, but its utility in providing measurable performance gains for downstream tasks remains under-explored. This paper bridges this gap by introducing drXAI, a novel methodology that repurposes XAI
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15847v1 Announce Type: cross Abstract: Metaphor in Arabic is a culturally grounded mechanism for constructing meaning, encoding cultural knowledge that shapes interpretation. Yet current Arabic language models typically collapse lexical, cultural, and metaphorical information into a single representational s
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16021v1 Announce Type: cross Abstract: Dialogue state tracking (DST) is one of the core components in task-oriented dialogue systems. At each turn in a conversation, DST estimates the user belief or dialogue state, which is used as input for downstream modules to predict system actions and generate responses
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.16065v1 Announce Type: cross Abstract: Retinal layer segmentation in Optical Coherence Tomography (OCT) is a fundamental step for extracting quantitative biomarkers of retinal structure. Indeed, there is a growing interest in the analysis of OCTs in the context of neurodegenerative diseases.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2507.21873v2 Announce Type: replace Abstract: Graph neural networks (GNNs) excel at predictive tasks on graph-structured data but often lack the ability to incorporate symbolic domain knowledge and perform general reasoning. Relational Bayesian Networks (RBNs), in contrast, enable fully generative probabilistic m
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2512.00319v3 Announce Type: replace Abstract: The Structure Gap between probabilistic LLM generation and deterministic schema requirements hinders automated workflows. We propose RL-Struct, a lightweight framework using Gradient Regularized Policy Optimization (GRPO) with a hierarchical reward function to align L
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.23786v2 Announce Type: replace Abstract: In recent years, the integration of multimodal machine learning in wellbeing assessment has offered transformative potential for monitoring mental health. However, with the rapid advancement of Vision-Language Models (VLMs), their deployment in clinical settings has r
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.22759v3 Announce Type: replace Abstract: While ubiquitous wearable sensors capture a wealth of behavioral and physiological information, effectively transforming these signals into personalized health insights is challenging. Specifically, converting low-level sensor data into representations capable of char
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.09689v3 Announce Type: replace Abstract: Snapshot-backed sandboxes make branching cheap while leaving evidence dependence unchanged. Branches can reuse a model, prompt, repository, tests, observations, or execution ancestor, so counting outputs can amplify one repeated error into high-confidence consensus.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2205.04599v2 Announce Type: replace-cross Abstract: Explainable Artificial Intelligence (XAI) is essential for trustworthy AI in healthcare, yet many existing methods rely on technical explanations that are difficult for clinicians and patients to interpret. We introduce Visualized Learning for Machine Learning (
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.10024v2 Announce Type: replace-cross Abstract: Long video summarization presents significant challenges for multimodal large language models (MLLMs), particularly in maintaining temporal fidelity over extended durations and producing summaries that are both semantically and temporally grounded. We introduce
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.15010v2 Announce Type: replace-cross Abstract: When do transformers commit to a decision, and what prevents them from correcting it? We introduce prolepsis: a transformer commits early, task-specific attention heads sustain the commitment, and no layer corrects it.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.02240v3 Announce Type: replace-cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls. Exi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.10439v2 Announce Type: replace-cross Abstract: We model human motor cortex, recorded during rest and motor-imagery BCI conditions, as a port-Hamiltonian system: a conservative interconnection (skew-symmetric coupling between band-limited neural phasors) together with a dissipative port whose state-dependent
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
What's changed Claude no longer runs the /verify and /code-review skills on its own; invoke them with /verify or /code-review when you want them
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
arXiv:2607.01153v2 Announce Type: replace-cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model has followed an instruction, refused appropriately, complied with a policy, resisted an embedded command, or misreported progress
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01211v2 Announce Type: replace-cross Abstract: Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime against unoptimized baselines and official reference patches. Their leaderboard sco
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2512.12477v3 Announce Type: replace Abstract: Estimating node importance in heterogeneous knowledge graphs is a fundamental problem underlying recommendation, search, and knowledge decision systems. However, most existing methods rely on pairwise message passing mechanisms that fail to capture higher-order intera
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14093v1 Announce Type: new Abstract: This paper presents a novel three level hierarchical learning architecture for autonomous UAV swarms performing search and rescue operations. Unlike conventional approaches that apply a single learning paradigm across all hierarchy levels, the proposed architecture integr
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14095v1 Announce Type: new Abstract: Retrieval Augmented Generation (RAG) has proven to be a widely successful process at improving the quality of outputs from a Large Language Model (LLM) for wider context. However, RAG systems typically retrieve context from flat document stores, which struggles when queri
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14309v1 Announce Type: new Abstract: The rapid development of Large Language Models (LLMs) and Artificial Intelligent (AI) powered autonomous agents has fundamentally changed the existing forms of software governance. In spite of the rigorous standards of transparency and account ability required according t
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14756v1 Announce Type: new Abstract: This research investigates the potential of Vision-Language Models (VLMs) to infer building typologies: Construction, Current Use, and Storeys from Google Street View (GSV) images. Predictions generated by VLMs are compared with inference by human experts (civil engineers
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15166v1 Announce Type: new Abstract: Most medical AI benchmarks measure whether a model knows the correct answer. MedFailBench asks a different question: which safety boundary failed?
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15202v1 Announce Type: new Abstract: Annotation quality is a major bottleneck in building reliable and explainable artificial intelligence (XAI) systems for mental health research. In depression-related datasets, labels are often assigned without structured evidence, symptom-level justification, or traceable
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15247v1 Announce Type: new Abstract: Evidence synthesis is crucial for turning primary research into reliable knowledge for science, medicine, education, and policy. Yet, quantitative evidence synthesis remains largely manual and difficult to scale.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14110v1 Announce Type: cross Abstract: Human dialogue involves more than exchanging information; it also expresses beliefs, emotions, and subjective cognitive styles. Yet current AI dialogue systems often enforce semantic uniformity, sacrificing diversity and interpretability.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14123v1 Announce Type: cross Abstract: Despite the proliferation of Explainable AI (XAI) techniques -- from feature attributions to sparse autoencoders -- explanations rarely influence real-world workflows. In practice, they are often generated and discarded without guiding meaningful action.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14152v1 Announce Type: cross Abstract: The persuasive power of data visualizations can go awry: for instance, in an explainable AI (XAI) context, visualizations can produce over-trust of predictive models. In this paper, we use a crowdsourced study to show that providing accurate (but superfluous or irreleva
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14203v1 Announce Type: cross Abstract: 3D simulation platforms are critical for autonomous driving because they enable end-to-end policy evaluation, thereby reducing development costs and improving safety. In recent years, neural simulation has become predominant, with methods such as NuRec playing a central
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14303v1 Announce Type: cross Abstract: Reasoning or inference-scaling models are the new generation of Large Language Models (LLMs) capable of complex problem solving. To investigate their problem-solving capability in physics, we evaluated model o4-mini by OpenAI on solving traditional, end-of-chapter probl
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14315v1 Announce Type: cross Abstract: In this paper, we present a comprehensive framework for assessing the explainability of various XAI methods, such as LIME and SHAP, across multiple datasets and machine learning models, with the ultimate goal of creating a unified multidimensional explainability score.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14340v1 Announce Type: cross Abstract: AI coding agents produce code faster than humans can review it. In our approach, the prover is the judge of whether the code is correct.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14568v1 Announce Type: cross Abstract: A companion study ran a 35B mixture-of-experts model on a 2011 NVIDIA Tesla C2075 (Fermi, sm_20, 6GB) as a GPU-prefill/CPU-decode hybrid, because the 4-bit model did not fit in device memory (arXiv:2606.24031). This report keeps the hardware and asks what a model that f
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14611v1 Announce Type: cross Abstract: A growing class of agentic systems maintain persistent state across sessions through memory files, behavioral preferences, and knowledge bases. While this makes agents more useful and self-improving, it also creates a new attack surface for prompt injections in which ma
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14659v1 Announce Type: cross Abstract: Interoperability between heterogeneous modeling tools remains a significant challenge in Model-Driven Engineering (MDE), particularly in the automotive domain where multiple modeling languages, as well as defacto standard proprietary and open-source tools coexist. This
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.14729v1 Announce Type: cross Abstract: Recent findings suggest that detection models for artificial intelligence (AI) cannot accurately identify AI-generated text and may exhibit bias against certain minority groups. In the present study, anecdotal claims that autistic writers more often have their work flag
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15006v1 Announce Type: cross Abstract: The broad adoption of Artificial Intelligence (AI), especially Generative AI, raises pressing questions about how users interact with these systems to produce new content. In this paper, we introduce the concept of authorship calibration, defined as users awareness of t
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.15275v1 Announce Type: cross Abstract: Recent robot foundation models operate with single-step or short-history visuomotor context. We introduce Test-Time-Training Robot Policies (RoboTTT), a robot model and training recipe that scale visuomotor context to 8K timesteps, three orders of magnitude beyond state
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.09142v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in online medical consultation, yet existing benchmarks remain poorly aligned with real clinical practice. Many rely on synthetic conversations or patient simulators, omit patient-uploaded medical images, or evalu
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.16351v2 Announce Type: replace-cross Abstract: Accurate taxonomic identification of parasitoid wasps within the superfamily Ichneumonoidea is essential for biodiversity assessment, ecological monitoring, and biological control programs. However, morphological similarity, small body size, and fine-grained int
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.09870v2 Announce Type: replace-cross Abstract: We investigate how looped transformers encode human preference, training lightweight evaluator heads on frozen Ouro-2.6B loop-iteration states on Anthropic HH-RLHF. v2: an erratum is prepended; the original manuscript is unchanged.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.11430v2 Announce Type: replace-cross Abstract: Mathematical knowledge is split between bibliographic databases (e.g., MathSciNet, zbMATH Open) and formal proof libraries (e.g., Lean mathlib), preventing unified access between published results and their formalizations. We propose a relational bridge-database
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.09957v2 Announce Type: replace-cross Abstract: This report studies on-device English-to-Traditional-Chinese subtitle translation for Taiwan under short inputs, short outputs, batch-size-one inference, low latency, and privacy constraints. These conditions limit the value of optimizations designed for long-co
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
What's changed Fixed single-segment dir/** allow rules like Edit(src/**) auto-approving writes to nested dir/ directories anywhere in the tree instead of only /dir Fixed a permission-check bypass affecting commands run in Windows PowerShell 5.1 sessions Fixed Bash permission checks to fail closed on file-descriptor red
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
The Copilot usage metrics REST API now reports repository-level activity. Two new endpoints return a daily, per-repository breakdown of pull request activity for Copilot coding agent and Copilot code review....
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
The Copilot usage metrics API now reports the GitHub Copilot app usage in the enterprise and organization 1-day and 28-day reports. This gives enterprise and organization admins visibility into the...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Copilot code review now utilizes a firewall, custom setup steps, and independent runner configurations. It now reads custom instructions from the head branch to allow for easy testing and validation...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
You can now select Fix with Copilot directly from Copilot code review pull request comments in GitHub Mobile. The button is available both on the pull request’s main view and...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from huggingface.co.
A series of emoji's: pancakes, tennis, sloth, fried egg, squidthumbs up
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Sarah Friar, CFO of OpenaAI, introduces a practical AI scorecard to measure ROI through useful work, cost per successful task, dependability, and return on compute.
API or pricing changes from openai.com can materially affect production costs and integration plans.
What's changed /fork now copies your conversation into a new background session (its own row in claude agents ) while you keep working; the in-session subagent it used to launch is now /subtask Added claude auto-mode reset to restore the default auto-mode configuration, with a confirmation prompt (pass --yes to skip) A
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
0.117.0 (2026-07-16) Full Changelog: v0.116.0...v0.117.0 Features api: add support for dreaming ( 642eee7 ) api: add support for MCP Tunnels ( d716df6 ) Bug Fixes credentials: keep credential material out of traceback frame locals via SecretStr ( aa93a4d ) Chores docs: small updates to field descriptions ( 75d8dcc ) do
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
The filter bar in GitHub Projects views now supports advanced search, so you can build the exact view you need with logical AND and OR instead of maintaining a separate...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Repository admins can now archive pull requests to remove them from public view without permanently deleting them. When a pull request is archived, it is closed and locked.
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Relive 60 years of soccer history at Mexico City’s Aztec Stadium with Google Earth and the ICA Foundation.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
GitHub Enterprise Cloud admins can now use the following REST API endpoints to programmatically manage Visual Studio Subscription (VSS) assignments: GET /enterprises/{enterprise}/visual-studio-subscriptions: Returns all VSS assignments for an enterprise, including... The post REST API endpoints for Visual Studio Subscrip
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
You can now build and test your Apple applications against Xcode 27 on GitHub-hosted macOS runners. This is now available in public preview.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
College students are eager to turn their dull dorm rooms into cozy spaces. Here are the Google Search trends we’re seeing.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
Four mobile phone screens illustrating Google Shopping features: personalized AI search results, a Google Lens visual search of a shoe, a product listing with a price-tracking button, and a virtual try-on feature showing a shirt on an avatar.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval
Agent builders should review whether this changes evaluation, orchestration, or long-running workflow assumptions.
Learn how OpenAI is making ChatGPT safer for teens with age-appropriate protections, learning tools, parental controls, and expert partnerships.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
Several alumni being interviewed
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
NotebookLM is now Gemini Notebook
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Text "Gemini Omni and Personal Avatars in Google Vids" surrounded by various images
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from blog.google.
Google partners with the Georgia Public Library Service to provide free Career Certificates and AI training to residents statewide.
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from blog.google.
Changes since langchain==1.3.13 release(langchain): 1.3.14 ( #38883 ) fix(langchain): only retry retryable exceptions in ToolRetryMiddleware ( #38845 ) feat(langchain): ToolErrorMiddleware ( #38781 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Today's decisions risk undermining vital privacy and security guardrails for millions of Europeans. We have repeatedly offered solutions to safeguard users while satisfy...
Teams giving assistants data or tool access should review the security failure mode described by blog.google.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
Parents using Instagram supervision tools will now be notified if their teen discusses suicide or self-harm with Meta AI.
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from about.fb.com.
Google DeepMind and Isomorphic Labs are sharing our joint approach to bioresilience and AI models.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
What's changed Auto mode is now available without CLAUDE_CODE_ENABLE_AUTO_MODE opt-in on Bedrock, Vertex AI, and Foundry; disable via disableAutoMode in settings Fixed the terminal freezing and keystrokes lagging while streaming responses containing very long lists, tables, paragraphs, or code blocks Fixed remote manag
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Changes since langchain==1.3.12 release(langchain): 1.3.13 ( #38787 ) feat(langchain): add meta extra and support langchain-meta in init_chat_model ( #38786 ) feat(openai): support explicit prompt caching ( #38762 ) chore(deps): refresh lockfiles ( #38746 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Changes since cli==0.4.30 chore(cli): allow langgraph-api versions up to 1.0.0 ( #8319 ) chore(deps): bump the minor-and-patch group in /libs/cli with 5 updates ( #8251 ) chore(deps): bump the minor-and-patch group in /libs/cli/js-examples with 6 updates ( #8246 ) chore(deps): bump the minor-and-patch group in /libs/cl
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
CodeQL is the static analysis engine behind GitHub code scanning, which finds and remediates security issues in your code. We’ve recently released CodeQL 2.26.0, which adds support for Kotlin 2.4.0,...
Teams giving assistants data or tool access should review the security failure mode described by github.blog.
To make secret scanning easier to understand, we’re updating the names we use for our detector types to better reflect how each one finds secrets. This is a naming change...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Changes since langchain-openai==1.3.4 release(openai): 1.3.5 ( #38785 ) feat(openai): support explicit prompt caching ( #38762 ) chore(model-profiles): refresh model profile data ( #38774 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Professional golfer Bryson DeChambeau partners with Google Health to track fitness metrics using Fitbit Air to bring data-driven athletic training to daily health routin...
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Studying for a test, but not sure where to start? Study notebooks, a new feature in the Gemini app, can help you get organized and learn more efficiently. Think of study ...
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
You can now retrieve every user’s progress against a multi-user budget from a single REST API endpoint. This makes it much faster to find who is close to their limit...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
GitHub Mobile now includes improved filters and sorting for Copilot sessions, making it easier to find the right session as your session list grows. You can now narrow your session...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
How Deutsche Telekom is becoming an AI-native telco with OpenAI-transforming customer service, employee workflows, network operations, and the future of voice.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
arXiv:2606.21428v3 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) language models are often described as ideal for resource-constrained inference. Each token activates only a small subset of experts, so the per-token compute cost, in floating-point operations (FLOPs), resembles that of a much smaller d
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02615v2 Announce Type: replace-cross Abstract: Generating structured artifacts with Large Language Models - e.g.\ database queries, threat framework mappings, entity schemas - is relatively straightforward; however, making them reliable enough for production deployments presents challenges. We present TAG, a
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03663v3 Announce Type: replace-cross Abstract: The accurate estimation of Above-Ground Biomass (AGB) in mature tropical forests remains a critical challenge in remote sensing, primarily due to the saturation of Synthetic Aperture Radar (SAR) signals in high-density areas and persistent cloud cover affecting
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06269v2 Announce Type: replace Abstract: Current large language models (LLMs) are stateless across inference sessions: their behavior is fully determined by input at inference time, and any higher-order cognitive architecture must be simulated at the application layer through prompt engineering and context m
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.07721v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) and agentic frameworks have advanced enterprise AI considerably, yet agents remain fundamentally reactive: they wait for a human query before acting. This paper argues that genuine enterprise productivity gains require proactive agents
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.07846v1 Announce Type: new Abstract: VectorizationLLM is a specialized Large Language Model based on Google open-weight LLMs. The model is designed to assist students to learn smart vectorization, time/wave vector analysis, piecewise functions, Fourier analysis, and differential equations in MATLAB.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08173v1 Announce Type: new Abstract: Black box auditing of language models is an essential pre-deployment tool, but it may miss subtle forms of misalignment and hidden information. To better elicit hidden information during an auditing process, we introduce \emph{overthinking}: the process of using reasoning
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08255v1 Announce Type: new Abstract: Large language models increasingly serve as teachers generating training data for smaller students. Prior multi-teacher knowledge distillation methods merge outputs without determining which frontier model teaches best, often relying on an LLM judge biased toward its own
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08573v1 Announce Type: new Abstract: Multimodal emotion and sentiment recognition is commonly addressed by early fusion, which concatenates modalities before classification, or late fusion, which combines independently trained unimodal predictors. Early fusion can be accurate but monolithic, while late fusio
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08758v1 Announce Type: new Abstract: Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.07743v1 Announce Type: cross Abstract: Self-organization is an emergent property of life, driven by the collective behavior of individual components acting on local information. Biological neurons, through local interactions transmitted through synapses, are able to learn efficiently and can adapt their conn
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.07935v1 Announce Type: cross Abstract: We present path_boost, a Python package for interpretable supervised learning on graph-structured input data. The package implements PathBoost, a gradient boosting algorithm that automatically discovers predictive labeled paths within graphs during the learning process.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08017v1 Announce Type: cross Abstract: Large-Language Models (LLMs) can be prone to flawed and unfaithful reasoning that decoding strategies like Self-Consistency (SC) fail to detect as they evaluate only final-answer agreement while ignoring the logical validity of intermediate steps. This raises three fund
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08034v1 Announce Type: cross Abstract: Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represent diverse value systems. We introduce PLURAL, a large-scale, value-focused preference dataset grounded in the Integrated Values Survey (IVS)
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08054v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly trusted to draft the artifacts of safety analysis such as, losses, hazards, Unsafe Control Actions (UCAs), and safety constraints, inside rigorous processes such as Systems-Theoretic Process Analysis (STPA). Yet a blind spot
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08143v1 Announce Type: cross Abstract: We present the results of HIPE-OCRepair-2026, an ICDAR competition on LLM-assisted OCR post-correction of historical documents. OCR post-correction remains a long-standing challenge in digital heritage: large-scale collections of digitized documents are affected by lega
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08162v1 Announce Type: cross Abstract: Whole slide images (WSIs) provide rich diagnostic information for computational pathology, but their gigapixel scale, stain variation, scanner differences, tissue artifacts, and limited expert annotation make robust model training challenging. This paper presents a mult
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08201v1 Announce Type: cross Abstract: Large-vocabulary instance segmentation is constrained by long-tailed category distributions and fine-grained inter-class ambiguity. While data synthesis offers a promising alternative, current paradigms have complementary limitations: text-to-image (T2I) methods inherit
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08331v1 Announce Type: cross Abstract: Understanding how artworks are created requires reasoning about the iterative decisions, material operations, and contextual influences that shape artistic production. While recent generative AI systems can synthesize artworks with high fidelity, they primarily model di
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08497v1 Announce Type: cross Abstract: Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing. However, they repeatedly feed all historical visual and textual inputs into a shared context window, limiting long-horizon multimo
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept. However, in vision-language models (VLMs), vanilla SAEs struggle to l
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.16453v3 Announce Type: replace Abstract: Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailBench, a data-grounded simulation benchmark for e
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.12138v3 Announce Type: replace Abstract: This position paper argues that Retrieval-Augmented Generation (RAG) systems exhibit a factual bias-optimizing for epistemic uncertainty reduction while ignoring the aleatoric uncertainty inherent in opinion-rich content. This misalignment demands a paradigm shift in
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.25984v2 Announce Type: replace Abstract: Large language models are increasingly deployed as investment research assistants, yet no benchmark tests whether they can accurately reconstruct and apply the specific procedural decision frameworks of expert investors. We introduce InvestPhilBench, a multi-layer ben
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2408.02379v2 Announce Type: replace-cross Abstract: Developing and certifying safe - or so-called trustworthy - AI has become an increasingly salient issue, especially in light of upcoming regulation such as the EU AI Act. In this context, the black-box nature of machine learning models limits the use of conventi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.20899v2 Announce Type: replace-cross Abstract: Scalable synthesis remains the gate between MOF discovery and industrial deployment, as scale-up know-how is fragmented across disparate reports. We introduce ScaleMOF, a literature-mined dataset and a positive-unlabeled learning strategy that fine-tunes large l
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.05050v2 Announce Type: replace-cross Abstract: Theoretical heterogeneous catalysis promises rapid catalyst discovery, yet computational and machine-learning predictions often deviate from experiment and stay confined to narrow material families, for want of a faithful, condition-aware catalytic simulator. We
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.12886v2 Announce Type: replace-cross Abstract: Interleaved thinking, where a unified multimodal model alternates between textual reasoning and visual generation, has shown promise on spatial and physical tasks. However, in complex long-chain scenarios, we identify a fundamental failure mode: generated images
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
Changes since 1.2.8 release(langgraph): 1.2.9 ( #8316 ) fix: updateState metadata/counters for delta channel ( #8315 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Profiling in PyTorch (Part 3): Attention is all you profile
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
The refreshed pull requests dashboard is now generally available at github.com/pulls. It gives you a single home to track, prioritize, and act on the pull requests that need your attention,...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Changes since langchain-fireworks==1.4.3 release(fireworks): 1.4.4 ( #38753 ) fix(fireworks): report cached prompt token usage ( #38751 ) chore(deps): refresh lockfiles ( #38746 ) chore(model-profiles): refresh model profile data ( #38663 ) chore: bump pytest from 9.1.0 to 9.1.1 in /libs/partners/fireworks ( #38594 ) c
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
OpenAI’s GPT-5.6 family is now rolling out in GitHub Copilot. GPT-5.6 comes in three variants, Sol, Terra, and Luna, so you can match the model to the job, whether that’s...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Finding the most efficient algorithm - whether designing a microchip, routing a logistics network or accelerating medical research - can be challenging, with many possib...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from blog.google.
Organization owners can now target a subset of repositories when enabling or disabling GitHub Code Quality, rather than applying it to every repository at once. This gives you more granular...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
You can now ask GitHub Copilot for a high-level overview of any repository you’re exploring for the first time. When you visit the home page of a repository you haven’t...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Learn how GPT-5.6 powers Microsoft 365 Copilot with stronger AI capabilities across Word, Excel, PowerPoint, Chat, and Cowork for faster, higher-quality work.
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from openai.com.
Studio provides a system of record for AI prompts and skills-versioned, owned, and traceable. Iterate fast, ship with control, and ensure consistent AI behavior.
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from mistral.ai.
More intelligence from every token, stronger performance per dollar, and more capability on demand for your hardest work.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
ChatGPT Work is an agent that can take action across your apps and files, stay with a project for hours if needed, and turn a goal into finished work.
Agent builders should review whether this changes evaluation, orchestration, or long-running workflow assumptions.
Details about the OpenAI Bio Bounty program
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
Collage of different pairs of people interacting
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
arXiv:2606.28421v2 Announce Type: replace-cross Abstract: Text-to-image (T2I) diffusion models typically require substantial computational resources and cloud infrastructure, posing significant challenges for edge deployment in terms of latency, cost, and user privacy. We present JuZhou 1.0, an ultra-lightweight T2I fo
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05419v2 Announce Type: replace-cross Abstract: Accurate and timely channel state information (CSI) is essential for next-generation wireless systems, yet existing works treat CSI compression and CSI prediction as separate problems, both in academia and in current 3GPP studies. Consequently, channel aging rem
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05876v2 Announce Type: replace-cross Abstract: LLM serving optimization typically benchmarks many configurations and reaches for heavy profilers when latency targets are missed. We argue for the reverse discipline: estimation is the analytical layer of profiling -- without it, optimization degenerates to gri
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06202v2 Announce Type: replace-cross Abstract: The deployment of Mixture-of-Experts (MoE) models on production high-bandwidth superpods, such as NVIDIA's NVL72/576 and Huawei's CloudMatrix384, introduces critical challenges beyond raw interconnect bandwidth. While these systems provide unified global address
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06760v1 Announce Type: new Abstract: Autonomous systems under partial observability act on beliefs, not raw sensor events. QANTIS treats the quantum processor as a calibrated belief-update service in that loop: it receives a prior and an observation model, estimates the rare-event evidence term, and returns
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.07391v1 Announce Type: new Abstract: Mathematical reasoning benchmarks typically provide all facts needed to solve each problem, while interactive benchmarks often mix reasoning with tools, retrieval, and long-horizon dialogue. We introduce MIRA-Math, a benchmark for a narrower diagnostic capability: solving
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.07663v1 Announce Type: new Abstract: AI systems increasingly participate in their own improvement: revising their outputs, adapting their own harnesses during deployment, training on data they generate, and, increasingly, conducting AI research itself. This literature is described under a vocabulary ("self-r
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06598v1 Announce Type: cross Abstract: Heart rate measurement is one of the key requirements for real-time health monitoring, in particular for health caring of elderly people. Traditional heart rate measurement relies on contact sensing mechanisms such as some heart rate measurement devices at medical hospi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06631v1 Announce Type: cross Abstract: Video Diffusion Models (VDMs) have demonstrated superior generation quality but suffer from prohibitive computational costs. While recent few-step distillation techniques significantly accelerate inference, they typically enforce a static model architecture across all d
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06940v1 Announce Type: cross Abstract: The remarkable performance of large language models (LLMs) in linguistic tasks underscores an urgent need for comprehensive evaluation of their response quality. Prevailing methods, often confined to singular dimensions, fall short of capturing the full spectrum of mode
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06963v1 Announce Type: cross Abstract: Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, Copilot, Stable Diffusion by OpenAI, Anthropic, Google, Meta, Microsoft, Stability AI, respectively, are revolutionizing cybersecurity, enabling both automated defens
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06988v1 Announce Type: cross Abstract: Steering robot foundation models (RFMs) toward new task variants or user-preferred behaviors remains challenging, often requiring additional robot demonstrations, task-specific fine-tuning, or long-context conditioning. We present WAM-TTT, a test-time training framework
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.07117v1 Announce Type: cross Abstract: In text-to-image in-context learning (T2I-ICL), a model has to infer a latent compositional pattern from fewshot demonstrations for generating a query image. Recent studies show that state-of-the-art multimodal large language models struggle with this setting, particula
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.07207v1 Announce Type: cross Abstract: We analyze how four forces restructure the AI industry over 2026-2030: the DRAM/HBM price surge, frontier-capable open-weight models (GLM-5.2), rapid inference-efficiency gains (near-Shannon-limit KV-cache compression, lightweight local runtimes), and the entry of Meta
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.07235v1 Announce Type: cross Abstract: Explainability remains a key issue in reinforcement learning (RL). Distilling an interpretable policy from an agent trained in a complex environment is particularly challenging when the action space is continuous.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.07313v1 Announce Type: cross Abstract: Pairwise comparison (PC) via pairwise reciprocal matrices (PRMs) is central to the Analytic Hierarchy Process (AHP). Although the traditional eigenvector method is widely applied to derive priorities, its theoretical robustness in reflecting true priority vectors remain
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.07401v1 Announce Type: cross Abstract: While whole-body multimodal medical imaging scanners have been increasingly recognized for more effective medical applications, the excessive long acquisition time in PET-MR scanning is a major obstacle in more efficient clinical practice. Deep learning-based MRI transl
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.07500v1 Announce Type: cross Abstract: Time series classification (TSC) is dominated by a two-stage paradigm: train a feature encoder -- either from scratch on the target dataset or via pretraining on large corpora -- and then fit a task-specific classifier on top. While effective, this decoupling optimizes
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.23802v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual reasoning and understanding tasks but still struggle to capture the complexity and subjectivity of human emotions. Existing approaches based on supervised fine-tuning often suffer from l
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.29693v3 Announce Type: replace Abstract: A robust decision-making process must take into account uncertainty, especially when the choice involves inherent risks. Because artificial intelligence (AI) systems are increasingly integrated into decision-making workflows, managing uncertainty relies more and more
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2511.18735v3 Announce Type: replace-cross Abstract: In this work, we define Foresight Intelligence as the capability to anticipate and interpret future events-an ability essential for applications such as autonomous driving, yet largely overlooked by existing research. To bridge this gap, we introduce FSU-QA, a n
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.15685v2 Announce Type: replace-cross Abstract: Omnimodal large language models (OmniLLMs) jointly process audio and visual streams, but the resulting long multimodal token sequences make inference prohibitively expensive. Existing compression methods typically rely on fixed window partitioning and attention
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.21489v2 Announce Type: replace-cross Abstract: AI agents have become increasingly capable at isolated software engineering (SWE) tasks such as resolving issues on Github. Yet long-horizon tasks involving multiple interdependent subtasks still pose challenges both with respect to accuracy, and with respect to
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.26772v2 Announce Type: replace-cross Abstract: Automated semantic annotation of broadcast television content presents distinctive challenges, combining structured audiovisual composition, domain-specific editorial patterns, and strict operational constraints. While multimodal large language models (MLLMs) ha
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.25605v2 Announce Type: replace-cross Abstract: Introduction: Semantic search, which retrieves documents based on conceptual similarity rather than keywords, offers advantages for retrieval of clinical information. However, deploying semantic search across health systems, comprising hundreds of millions of cl
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.05403v2 Announce Type: replace-cross Abstract: Language models increasingly act as epistemic proxies, synthesizing evidence from multiple sources to inform decisions. Whether they evaluate the quality of that evidence, or merely aggregate it based on surface presentation, remains poorly understood.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.07094v2 Announce Type: replace-cross Abstract: Scientific workflows increasingly generate structured JSON data that is easy to exchange but difficult to interpret consistently across systems due to lacking semantic interoperability. While JSON Schema ensures structural validation, it provides no native suppo
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
Changes since langchain-openai==1.3.3 release(openai): 1.3.4 ( #38731 ) fix(openai): suppress Pydantic serializer warning on structured output parsed field ( #37727 ) test(openai): skip Codex VCR tests before cassette setup ( #38690 ) chore: bump the minor-and-patch group across 3 directories with 11 updates ( #38587 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Changes since langchain==1.3.11 release(langchain): 1.3.12 ( #38730 ) fix(langchain): propagate interrupts through ToolRetryMiddleware ( #38722 ) fix(langchain): avoid shared process-group kill in shell middleware ( #36359 ) fix(langchain): sanitize anthropic cache markers on fallback retries ( #37867 ) style: fix some
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
GitHub Advanced Security enterprise customers can now publish internal security advisories. Innersource advisories work similarly to GitHub’s open source advisories, but their visibility is restricted to repositories owned by the...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
What's changed Added an auto mode rule that blocks tampering with session transcript files Fixed --json-schema silently producing unstructured output when the schema was invalid, and schemas using the format keyword being rejected Fixed a message sent while Claude was working being silently lost when the turn ended at
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Organizations can now mandate where GitHub Copilot sends OpenTelemetry (OTel) data, so telemetry flows to an approved collector without each developer setting OTEL_* environment variables. The configuration is delivered through...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Enterprise administrators can now deliver managed GitHub Copilot settings directly to devices through native mobile device management (MDM) and file-based configuration, in addition to the existing server-managed channel. This is...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Changes since langchain-core==1.4.8 release(core): 1.4.9 ( #38728 ) fix(core): improve langsmith loader error messages ( #35648 ) fix(core): output parser bugs in xml.py and pydantic.py ( #35641 ) style(core): fix some ruff preview rules ( #38656 ) fix(core): avoid dict shadowing in language models ( #38480 ) fix(core)
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
This changelog covers VS Code v1.123 through v1.127, shipped throughout June and early July 2026. The latest VS Code releases build on the Copilot experience developers use every day, making...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Agent builders should review whether this changes evaluation, orchestration, or long-running workflow assumptions.
The actions/setup-java v5.5.0 release adds cryptographic signature verification for downloaded JDKs, support for a new distribution, and several quality-of-life improvements for Maven users. Here’s what changed since v5.4.0.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
With Video Remix in Google Photos, you can transform ordinary videos into share-worthy moments in just a few taps.
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from blog.google.
2 men standing outside Henry's House of Coffee
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from blog.google.
npm v12 is now generally available and tagged latest. This major release turns on the install-time security defaults we announced in June, and it’s also where we begin a deprecation...
Teams giving assistants data or tool access should review the security failure mode described by github.blog.
Learn how OpenAI approaches government and national security partnerships, with principles for responsible AI use, democratic accountability, and public safety.
Teams giving assistants data or tool access should review the security failure mode described by openai.com.
Google is announcing a long-term agreement with Thryve.Earth for 260,000 tons of carbon removal.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
A new analysis from OpenAI reveals issues in SWE-Bench Pro, a popular coding benchmark, raising concerns about reliability and accuracy in evaluating AI models.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
Introducing Robostral Navigate: 8B model achieving 76.6% on R2R-CE with just a single RGB camera. No depth sensors, LiDAR, or multiple cameras needed.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
OpenAI Academy and the Walton Family Foundation are bringing hands-on AI Skills Jams to help K-12 educators build practical AI skills for the classroom.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
GitHub Mobile now supports fixing pull request merge conflicts with Copilot cloud agent, making it easier to unblock pull requests while you’re on the go. When a pull request has...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Live coding agent notifications on GitHub Mobile now support remote Copilot CLI sessions, making it easier to stay connected to agent work that starts outside of GitHub Mobile. When a...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Street View imagery of Blue Eye (Albania), Kotor Town Walls (Montenegro), Skopje Fortress (North Macedonia), and Belgrade Fortress (Serbia)
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
The Copilot usage metrics API now reports two additional code-review velocity metrics for each AI adoption phase, extending the adoption phase cohorts fields available in the enterprise and organization reports....
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
arXiv:2606.20023v2 Announce Type: replace-cross Abstract: As LLM agents increasingly select tools autonomously, their choices among tools with different privileges become safety-relevant. However, prior tool-selection studies focus on safety-agnostic metadata preferences, leaving privilege-sensitive choices underexplor
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2501.07892v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong performance in automated code generation, with few-shot prompting widely used for its simplicity and effectiveness. However, few-shot methods depend on curated or manually crafted reference examples, limiting their
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02998v2 Announce Type: replace-cross Abstract: Controllable generative models of 3D medical images can synthesize volumes with specified clinical attributes, but this demands samples that are simultaneously high-fidelity, natively 3D, and faithful to the requested conditioning. We present CONFLUX, a latent d
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03819v2 Announce Type: replace-cross Abstract: Challenges remain in ego-centric 3D scene generation due to limited view overlap and the dominant influence of individual perspectives on scene interpretation. These factors hinder the creation of viewpoint-consistent and semantically aligned visual content, as
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05352v2 Announce Type: replace-cross Abstract: We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions. Whereas single-player world models treat the other agents as part of the environment, ours conditions on the action streams of multiple agen
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05573v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) enable the automatic generation of parametric 3D designs from natural-language specifications. This chapter presents an empirical study of foundation models for automatic Computer-Aided Desi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05943v1 Announce Type: new Abstract: Training multimodal search agents to perform multi-hop reasoning remains challenging due to a fundamental structural disconnect: existing pipelines construct training data, search environments, and reward signals independently, causing synthesized structural metadata to b
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06066v1 Announce Type: new Abstract: The Vehicle Routing Problem (VRP) and its variants represent some of the most practically consequential optimization challenges in modern logistics and urban mobility. In this study, we address a dynamic, online variant combining elements of the VRP and the Orienteering P
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06407v1 Announce Type: new Abstract: The XAI community has studied a wide range of queries and scores for explaining predictions of ML models. From a data management perspective, this proliferation of explanation notions calls for declarative query languages in which such notions can be specified, combined
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05399v1 Announce Type: cross Abstract: Large language model serving is increasingly limited by KV-cache growth under long-context workloads, yet existing KV-cache compression techniques are difficult to compare because they were evaluated on different models, tasks, budgets, and serving stacks. This paper pr
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05403v1 Announce Type: cross Abstract: This paper aims to synthesize empirical research on AI tools used to support English as a second/foreign language (EL2) learners in Arab University classrooms (AUCs) between Jan 1st 2023 and Aug 31st 2025. We utilized 3 large datasets, namely Google Scholar, Web of Scie
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05404v1 Announce Type: cross Abstract: Frontier AI's labor-market effects matter to workers, firms, and policymakers, but current evidence generally comes from a handful of high-income economies. The capabilities of frontier AI are jagged across work tasks and national economies diverge in how they allocate
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05443v1 Announce Type: cross Abstract: Scientists increasingly rely on open-source tools to support their research workflows, yet discovering relevant software among over 600 million GitHub repositories remains challenging. Existing code search benchmarks focus on general software engineering tasks and fail
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05449v1 Announce Type: cross Abstract: Accurate work-zone geometry perception is critical for intelligent transportation systems, and ultra-wideband sensing offers a low-cost approach for infrastructure-aided reconstruction. However, outdoor UWB ranging is often degraded by non-line-of-sight propagation, bur
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05552v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly issue judgments read as binary verdicts, and a growing literature reports such judgments shifting under logically irrelevant changes of wording - among them an amplified yes-no bias on moral dilemmas, absent in humans. A single
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05585v1 Announce Type: cross Abstract: FaceMesh2HPO is a framework for classifying facial phenotypic descriptors aligned with the Human Phenotype Ontology (HPO) to support clinical diagnosis. Using annotations from 124 clinicians across 10 disorders (107 HPO terms) combined with non-syndromic controls, we ge
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05614v1 Announce Type: cross Abstract: Document comprehension is a challenging yet impactful task for Multimodal Large Language Models, especially as these systems see growing adoption in real-world, human-centric applications. However, this adoption is limited for low-resource languages such as Bangla due t
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05679v1 Announce Type: cross Abstract: Language models (LMs) exhibit problematic biases, such as stereotypes. Effectively analyzing and mitigating such biases requires accurate and generalizable evaluation methods of the underlying associations.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05744v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) is the dominant way coding agents discover and invoke external tools. A server advertises each tool through a tools/list handshake that returns a name, a natural-language description, and a JSON input schema.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05846v1 Announce Type: cross Abstract: Accurate ranking of antibody candidates according to their binding affinity is essential for therapeutic antibody discovery. However, existing methods treat affinity comparisons independently and ignore the contextual information encoded in other labeled comparisons, li
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05970v1 Announce Type: cross Abstract: Dataset search depends heavily on metadata, making LLM-generated metadata a consequential form of synthetic content in retrieval systems. We study six metadata-generation settings for RDF datasets, ranging from simple rewriting to profile-grounded and agentic graph-base
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06132v1 Announce Type: cross Abstract: Multi-Pool Chemical Exchange Saturation Transfer (CEST) MRI provides valuable metabolic information but is clinically limited by long acquisition times. Although sparse sampling reduces scanning time, reconstructing high-resolution Z-spectra from limited data remains an
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06296v1 Announce Type: cross Abstract: This paper presents the design and evaluation of a maintainable hybrid generative architecture for automated music harmony generation from melody. The proposed system combines quantum-inspired candidate exploration over overlapping melodic contexts with explicit rule-ba
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06306v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated growing competence in web page generation. However, existing text-driven approaches rely on complex prompts that impose substantial demands on users and offer limited expressivity for page layout and cross-page visual coher
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06481v1 Announce Type: cross Abstract: We present PACR-Video, a parameter-efficient framework for multi-shot long video extrapolation that preserves recurring entities, scene structure, visual style, and causal progression without full generator fine-tuning. PACR-Video keeps a text-to-video diffusion transfo
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.06505v1 Announce Type: cross Abstract: GitHub hosts hundreds of millions of public repositories, but the platform exposes no native mapping from repositories to standardized industry sectors. This gap limits empirical work on the geography of innovation, the industrial composition of open-source production
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.13566v2 Announce Type: replace Abstract: Current discussions of AI in scientific discovery are often dominated by two visible capabilities: search over existing knowledge and execution through optimization, simulation, and automation. Both are important, but neither fully captures the central act of discover
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2504.20342v2 Announce Type: replace-cross Abstract: Reflexion is an AI-powered prototype designed to explore structured emotional self-reflection. By integrating emotion detection, layered reflective prompting, and metaphorical storytelling generation, Reflexion was intended to support users in autonomous emotion
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2505.15516v3 Announce Type: replace-cross Abstract: While eXplainable AI (XAI) has advanced significantly, few methods address interpretability in embedded vector spaces where dimensions represent complex abstractions. We introduce Distance Explainer, a novel method for generating local, post-hoc explanations of
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2509.09513v3 Announce Type: replace-cross Abstract: Biophysical diffusion MRI models like Neurite Exchange Imaging (NEXI) are essential for probing gray matter microstructure, estimating compartment diffusivities, neurite fraction, and exchange time. However, NEXI's multi-shell, multi-diffusion-time requirements
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2509.23876v3 Announce Type: replace-cross Abstract: Autoregressive (AR) models based on next-scale prediction have emerged as a powerful tool for image generation, but they face a critical weakness: information inconsistencies between patches across timesteps introduced by progressive resolution scaling. These in
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2512.18542v3 Announce Type: replace-cross Abstract: AI coding assistants produce vulnerable code in 45\% of security-relevant scenarios~\cite{veracode2025}, yet no public training dataset teaches both traditional web security and AI/ML-specific defenses in a format suitable for instruction tuning. We present Secu
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2512.23236v4 Announce Type: replace-cross Abstract: Making deep learning recommendation model (DLRM) training and inference fast and efficient is important. However, this presents three key system challenges - model architecture diversity, kernel primitive diversity, and hardware generation and architecture heter
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.14761v2 Announce Type: replace-cross Abstract: Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability. Moreover, the current meta-learning literature uses key terms like "universal" and "general-purpose" inconsistently and lacks
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.04024v2 Announce Type: replace-cross Abstract: Ambiguous 3D medical image segmentation often involves boundaries where different expert delineations are non-identical yet clinically plausible. Modeling such inter-observer variability requires a careful balance between diversity and anatomical fidelity: deter
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.15600v2 Announce Type: replace-cross Abstract: Accurate process supervision remains a critical challenge for long-horizon robotic manipulation. A primary bottleneck is that current video MLLMs, trained primarily under a Supervised Fine-Tuning (SFT) paradigm, function as passive "Observers" that recognize ong
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.19216v2 Announce Type: replace-cross Abstract: Understanding and generating 3D objects as compositions of meaningful parts is fundamental to human perception and reasoning. However, most text-to-3D methods overlook the semantic and functional structure of parts.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.13974v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood. In this work, we study massive activations:
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.22775v2 Announce Type: replace-cross Abstract: Real-time cognitive load assessment from eye-tracking signals could enable adaptive human-centered AI in safety-critical applications such as driver vigilance monitoring or automated flight deck assistance, yet two challenges persist: handling frequent data miss
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
Hermes Agent v0.18.2 (v2026.7.7.2) Release Date: July 7, 2026 Same-day patch on top of v0.18.1, picking up the WhatsApp Baileys dependency fix needed for tagged-release Docker builds. What's in this patch fix(whatsapp): unpin Baileys from git commit, use published 7.0.0-rc13 ( #60643 ) - the WhatsApp bridge dependency
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
This update brings Codex as a new agent provider in public preview, expands the Customizations editor with Hooks support and richer MCP server management, and introduces custom model support configured...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Hermes Agent v0.18.1 (v2026.7.7) Release Date: July 7, 2026 Patch release. This tag rolls up the ~660 PRs merged since v0.18.0 (July 1) - bug fixes, hardening, and in-progress feature work - into a stable tagged release for downstream consumers (Docker images, hosted deployments, PyPI installs).
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
What's changed Fixed hook events not streaming during SessionStart hooks in headless sessions, which could cause remote workers to be idle-reaped mid-hook
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
On July 1, 2026, we announced Kimi K2.7 would be available to Copilot Pro, Pro+, and Max plans. The model is now additionally available on Copilot Business and Copilot Enterprise...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Native-speed vLLM transformers modeling backend
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
A new generation of voice models for natural human-AI interaction, now powering ChatGPT Voice.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
From Hugging Face to Amazon SageMaker Studio in one click
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
What's changed Added a warning when your login is about to expire, so you can re-authenticate before background sessions are interrupted Added a grey ⏸ badge to the footer when in manual permission mode, making the active mode always visible Added the session's additional working directories to MCP roots/list , with no
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Muse Image is the first image generation model from Meta Superintelligence Labs, now available in Meta AI.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
GiveDirectly Staff talking to a crowd of people
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Enterprise admins can now create cost center user-level budgets directly in the billing UI where you manage cost centers and budgets. This feature is available for GitHub Enterprise Cloud.
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
To help you understand ownership and impact of a leaked secret, GitHub secret scanning surfaces enriched metadata for supported secret types. Extended metadata checks are now generally available, including support...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Three new FireSat satellites have launched, expanding a network that uses Google AI to help fire agencies detect early-stage wildfires.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Hugging Face Models on Foundry Managed Compute
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
You can now restrict who can dismiss pull request reviews directly in GitHub repository rulesets. This capability is generally available and gives you precise control over who can clear an...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
The GitHub Copilot app is now available on every Copilot plan. Sign in with your GitHub account to start agent-driven development from your desktop.
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
The Copilot Billing Preview app will be retired on August 3, 2026. If you use it to review your GitHub Copilot spend, you can get even greater visibility directly in...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Managed agents feature bundle launch
Agent builders should review whether this changes evaluation, orchestration, or long-running workflow assumptions.
arXiv:2606.16428v3 Announce Type: replace-cross Abstract: Effective personalized AI-assisted learning demands systems that can not only generate accurate learner-specific educational materials, but also dynamically adapt their instruction to diverse learners. However, existing educational agents have primarily focused
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.25996v3 Announce Type: replace Abstract: We introduce Autodata, a general method that enables AI agents to act as data scientists who build high quality training and evaluation data. We show how to train (meta-optimize) such a data scientist agent, so that it learns to create even stronger data.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30997v2 Announce Type: replace Abstract: We present a three-phase deep reinforcement learning system for personalized portfolio management that addresses three limitations shared by all prior financial RL work: 1) ticker lock-in, 2) monolithic objectives , and 3) static user models. Phase 1 pretrains a ticke
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30695v2 Announce Type: replace-cross Abstract: Single-cell drug perturbation models should capture transcriptional response magnitude and whether a treatment changes the proliferative state of the cell. This is difficult because cell-cycle variation is often treated as a nuisance factor, and benchmark proces
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00955v2 Announce Type: replace-cross Abstract: Implicit neural representations (INRs) are well suited to cardiac motion estimation, providing continuous, compact representations of motion fields. However, fitting an INR to each image sequence is time-consuming and sensitive to the optimisation trajectory.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2511.05747v4 Announce Type: replace Abstract: Long Chain-of-Thought (CoT) traces can improve reasoning accuracy, but repeatedly generating them is costly for smaller or latency-constrained language models. This paper studies a practical alternative: produce a rich rationale once with a capable \emph{thinking} mod
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01425v2 Announce Type: replace Abstract: Understanding large, complex codebases, especially those with obfuscated structures and incomplete documentation, remains a significant challenge. Existing code summarization solutions often rely on a single language model or coding assistant like Claude Code, and tre
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01674v2 Announce Type: replace Abstract: In multi-source ECG deployment, models may need to incorporate new data sources when earlier raw ECGs cannot be retained or replayed. Freezing a pretrained backbone and assigning each source an isolated classifier prevents parameter interference, but deployment still
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02116v2 Announce Type: replace Abstract: Autonomous AI agents increasingly depend on external knowledge stores, yet most retrieval pipelines provide relevance without durable guarantees of provenance, version identity, integrity, traceability, or point-in-time reconstruction. We formalize this as context gov
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03091v1 Announce Type: new Abstract: Silicon sampling-using large language models (LLMs) to simulate human survey respondents-has emerged as a promising approach for augmenting traditional survey research. However, most evaluations rely on distributional comparisons rather than individual-level prediction, w
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03394v1 Announce Type: new Abstract: Real time location data derived from mobile applications is a powerful tool for addressing various urban challenges, including tourism planning, parking management, bus route optimization, and resource allocation. Besides, it offers invaluable insights for shaping strateg
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03397v1 Announce Type: new Abstract: Text-to-Image diffusion models often propagate harmful bias inherited from the training data. Existing bias mitigation techniques typically intervene only at the text encoder or provide inference-time guidance, often leading to generations that collapse into semantically
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03702v1 Announce Type: new Abstract: Large language model (LLM) agents have shown strong decision-making capabilities in long-horizon interactive tasks, yet they still struggle to effectively leverage failed trajectories: full retries incur high interaction costs, while experience retrieval tends to dilute c
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03748v1 Announce Type: new Abstract: Unified multi-modal models (UMMs) have shown promising interleaved text-image reasoning capabilities, yet effectively optimizing such multi-turn generation via reinforcement learning (RL) remains an open challenge. Existing approaches apply RL exclusively to text steps, r
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04089v1 Announce Type: new Abstract: Lifelong agents need more than larger context windows and better retrieval. They need memories that can persist, evolve, and be corrected without forcing the serving stack to recompute the same history on every turn or silently reuse stale runtime state.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04240v1 Announce Type: new Abstract: The transition of Large Language Models (LLMs) from passive generators to autonomous agents has introduced significant challenges in reliability, security, and state management. Current agentic architectures are often constructed ad-hoc, prone to hallucination cascades, i
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05007v1 Announce Type: new Abstract: This paper introduces a quantum-inspired computational framework for harmonic decision-making in music. The proposed approach formulates harmonization as an optimization problem within a structured combinatorial space, where multiple candidate chord sequences are evaluate
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05202v1 Announce Type: new Abstract: Agent self-evolution in long-horizon LLM systems is largely procedural: useful experience is not merely stored information, but reusable procedures for searching, debugging, and verification. Yet current evaluations do not isolate this form of transfer.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05297v1 Announce Type: new Abstract: Recent LLM agents tackle increasingly long-horizon, open-ended tasks, and external skills, reusable procedural knowledge supplied to the agent, further extend this capability. However, a fixed, hand-authored skill is rarely optimal, and cannot adapt to the diversity of ta
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.20691v1 Announce Type: cross Abstract: Ontologies are useful structures to organize and maintain information that can be understood both by humans and systems. However, since their manual crafting is a laborious task, many specific domains lack reference ontologies.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02564v1 Announce Type: cross Abstract: Computational models of the human heart are widely used to study electromechanical and fluid-dynamical cardiac function and to support applications such as in silico clinical trials. However, most studies remain limited to single or patient-specific anatomies, restricti
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02622v1 Announce Type: cross Abstract: Multiplex CRISPR-Cas9 gene editing requires selecting one guide RNA per target gene subject to cross-gene interactions: a constrained combinatorial problem that can be formulated as a Quadratic Unconstrained Binary Optimization (QUBO) and solved via the Quantum Approxim
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02640v1 Announce Type: cross Abstract: Real-time interaction models -- Moshi, MiniCPM-o, Qwen-Omni -- turn serving into a periodic real-time task: on every frame a session ingests streaming audio and must respond by a recurring wall-clock deadline, while its KV cache grows monotonically and stays pinned for
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02689v1 Announce Type: cross Abstract: As wearable devices enable continuous first-person recording, AI assistants must reason across long time horizons to recall past experiences-a capability known as episodic memory. Current benchmarks often rely on offline evaluation with access to entire video files, fai
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02734v1 Announce Type: cross Abstract: Rapid growth in social media has transformed global communication by enabling fast information exchange, but it has also accelerated the spread of misinformation. Fake news, manipulated content, and provocative narratives are increasingly linked to social unrest, politi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02886v1 Announce Type: cross Abstract: Deploying AI-generated video detectors in real-world services demands an ultra-low false positive rate (FPR) on real videos to avoid falsely rejecting authentic content, a regime where standard metrics such as AUROC fail to reflect actual operating behavior. We introduc
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02963v1 Announce Type: cross Abstract: Dense video captioning aims to generate temporally grounded descriptions of video events, benefiting both event-level video understanding and generation. In this domain, autoregressive video large language models have emerged as a prevalent paradigm due to their strong
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03253v1 Announce Type: cross Abstract: As hematoxylin & eosin (H&E) staining constitutes the primary entry point in routine diagnostic workflows, computer-aided diagnosis from whole-slide H&E images is of particular clinical relevance. However, substantial variability in specimen preparation, staining protoc
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03298v1 Announce Type: cross Abstract: Foundation models for Earth systems have so far been trained primarily on physical climate and weather data, with limited representation of the human systems that both drive and respond to environmental change. The lack of a unified global training resource that combine
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03447v1 Announce Type: cross Abstract: Knowledge graphs (KGs) that underpin Graph-based Retrieval-Augmented Generation (Graph-RAG) are increasingly built automatically by LLM-driven extraction rather than curated by experts. Proper evaluation would require instrumenting all pertinent stages: extraction, grap
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03466v1 Announce Type: cross Abstract: This study aims to predict Tumor, Node, and Metastasis (TNM) stage labels independently, with the Cancer Genome Atlas (TCGA) pathology report as the sixth shared task of SMM4H-HeaRD 2026. The problem is framed as three multi-label classification tasks.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03624v1 Announce Type: cross Abstract: This paper challenges the assumption that vision-language models (VLMs) require fixed patch-based 2D vision features. Analyzing fine-tuned vision encoders, we find that representations become increasingly abstract and less spatially coherent during VLM training.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03644v1 Announce Type: cross Abstract: Decades of orbital missions have produced multi-modal remote sensing data for the Moon, spanning optical imagery, spectroscopy, thermal emission, radar, gravity, and elemental composition. Yet these datasets remain fragmented across archives, and no benchmark exists for
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03652v1 Announce Type: cross Abstract: Transformer blocks are prevalent in large language model (LLM) but present deployment challenges due to their challenging computational and memory demands. While prior work has typically optimized attention mechanisms or feed-forward networks (FFNs) separately, few hard
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03803v1 Announce Type: cross Abstract: The growing demand for image-to-video creation on mobile devices has increasingly focused on cinematic motion effects like bullet time, dolly zoom, slow motion, etc. While Diffusion Transformers (DiTs) exhibit strong performance in video generation, their large paramete
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03929v1 Announce Type: cross Abstract: Multi-Meta-RAG improves retrieval for multi-hop question answering by filtering a vector store on metadata (the news source) that it extracts from each query by prompting gpt-3.5-turbo. We show this proprietary, free-form extractor can be replaced by a local, determinis
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03951v1 Announce Type: cross Abstract: The reproducibility crisis in scientific research has received widespread recognition, thereby increasing the importance of meta-analyses that integrate statistical analyses from multiple studies. However, statistical methods often have ambiguous and implicit underlying
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.03994v1 Announce Type: cross Abstract: Modern language models generally represent text as sequences of discrete token embeddings, an assumption deeply rooted in current practice but rarely questioned. We challenge this representation, especially for Chinese, by replacing index-based token embeddings entirely
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04030v1 Announce Type: cross Abstract: Conditional functional dependencies (CFDs) are functional dependencies with a restricted scope: they specify the context in which a dependency holds and are useful for data-quality tasks, specifying complex integrity constraints, and extracting valuable insights from da
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04033v1 Announce Type: cross Abstract: Optimizer selection for large-scale model training has become a system-level design decision constrained jointly by compute, memory, tuning budget, and task diversity, yet the landscape of over one hundred methods remains fragmented. We therefore present OmniOpt, a unif
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04147v1 Announce Type: cross Abstract: Automated fine-grained perception of calligraphy styles--a task vital to cultural heritage preservation--remains a critical challenge for Large Vision-Language Models (LVLMs), largely constrained by existing datasets that suffer from modal mixture and flattened labels.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04277v1 Announce Type: cross Abstract: The pursuit of self-evolving AI raises a critical question: when is autonomous self-improvement sustainable rather than degenerative? Drawing an analogy to von Neumann's complexity threshold for self-reproducing automata, we argue that sustainable recursive self-improve
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04302v1 Announce Type: cross Abstract: We present HiFA4, a post-training operator-level design that executes both QK^T and PV in FlashAttention as 4-bit HIF4 Cube GEMMs for LLM inference on Ascend NPUs, while maintaining the online softmax state in FP16. To our knowledge, HiFA4 is the first Ascend-HIF4-targe
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04436v1 Announce Type: cross Abstract: Natural language requirements (NLRs) are essential for bridging communication gaps among diverse stakeholders in software development. However, the inherent ambiguity in NLRs can pose significant challenges.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04478v1 Announce Type: cross Abstract: Automated chest X-ray classification remains challenging due to severe class imbalance, co-occurring pathologies, and the loss of localized features in conventional architectures. To address these, we propose an explainable hierarchical multi-view ensemble framework for
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04510v1 Announce Type: cross Abstract: Emergent misalignment (EM) -- the broad misbehaviour a language model acquires after fine-tuning on narrow harmful data -- is mediated in Qwen2.5 models by a latent persona direction, and that direction is causal in open weights. Transplanting it into a model that share
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04668v1 Announce Type: cross Abstract: On-device LLM decoding is a hard-barriered CPU-SIMD computation that wants every core for milliseconds per token, while the rest of the OS wants those same cores continuously. A barriered gang cannot simply be dropped into a preemptive scheduler: an unannounced departur
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.04681v1 Announce Type: cross Abstract: Embodied Chain-of-Thought has emerged as a promising mechanism to enhance robot decision-making and interpretability in black-box Vision-Language Action (VLA) models. However, whether this verbalized Chain-of-Thought truthfully reflects the policy's underlying decision
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05052v1 Announce Type: cross Abstract: Human value detection is commonly formulated as sentence-level multi-label classification over the 19 refined Schwartz values, typically predicted as independent labels. Schwartz theory, however, describes them as a circular motivational continuum, in which adjacent val
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05120v1 Announce Type: cross Abstract: AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security has primarily focused on indirect prompt injection (IPI).
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.05353v1 Announce Type: cross Abstract: Watermarking methods embed imperceptible and verifiable signals into text generated by large language models (LLMs). Existing approaches include zero-bit schemes for distinguishing synthetic text from human writing and multi-bit schemes for embedding metadata.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2512.04632v2 Announce Type: replace Abstract: Orthogonality-based optimizers, such as Muon, have recently shown strong performance across large-scale training and community-driven efficiency challenges. However, these methods rely on a costly gradient orthogonalization step.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.14095v2 Announce Type: replace Abstract: Monitoring chain-of-thought (CoT) reasoning is a foundational safety technique for large language model agents; however, this oversight is compromised if models learn to conceal their reasoning. We explore steganographic CoT--where models hide secret reasoning within
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.06890v4 Announce Type: replace Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because these tool-use decisions are difficult to diagnose and control. Agents may skip required tool calls, invoke tools unnecessarily, or take actions whose conse
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2404.01299v3 Announce Type: replace-cross Abstract: Causal video question answering (QA) has garnered increasing interest, yet existing datasets often lack depth in causal reasoning. To address this gap, we capitalize on the unique properties of cartoons and construct CausalChaos!, a novel, challenging causal Why
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2508.16181v2 Announce Type: replace-cross Abstract: Cross-organizational collaboration in Model-Based Systems Engineering (MBSE) faces many challenges in achieving semantic alignment across independently developed system models. SysML v2 introduces enhanced structural modularity and formal semantics, offering a s
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2508.21010v3 Announce Type: replace-cross Abstract: Existing Causal-Why Video Question Answering (VideoQA) models often struggle with higher-order reasoning, relying on opaque, monolithic pipelines that entangle video understanding, causal inference, and answer generation. These black-box approaches offer limited
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2510.15476v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used as interfaces to information, code, and real-world services, making prompt-level security failures a practical concern. Although jailbreak attacks, defenses, datasets, and automated judgers have advanced rapidly
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2510.20692v3 Announce Type: replace-cross Abstract: Access control policies are reliability-critical configuration artifacts in cloud systems, yet administrators frequently struggle to verify that a policy permits exactly what they intend. This verification gap cannot be remedied by using LLMs to synthesize polic
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2512.05672v2 Announce Type: replace-cross Abstract: Recent approaches in controllable novel view video generation often rely on fine-tuning pre-trained Video Diffusion Models (VDMs). This dominant paradigm is computationally expensive and frequently suffers from catastrophic forgetting of the model's original gen
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2512.22240v5 Announce Type: replace-cross Abstract: Machine learning models are primarily judged by predictive performance, especially in applied genomics, where explanations are read as biological findings. In practice, reported gene panels are stabilised by averaging, ranking, or taking consensus over the many
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.06941v3 Announce Type: replace-cross Abstract: Large language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.g., ``wait, that's not right'') and continuing on-topic even while the steering perturbation remains active. We term this Endogenous
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.06576v2 Announce Type: replace-cross Abstract: The integration of Large Language Models (LLMs) into autonomous driving has attracted growing interest for their strong reasoning and semantic understanding abilities, which are essential for handling complex decision-making and long-tail scenarios. However, exi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.13259v3 Announce Type: replace-cross Abstract: When a decoder-only transformer is forced to process matched correct and incorrect single-token continuations of a factual query, the two pathways through hidden-state space diverge: displacement vectors from the query-only representation keep near-equal magnitu
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.09544v2 Announce Type: replace-cross Abstract: Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that generalizes broadly. Wh
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.16870v2 Announce Type: replace-cross Abstract: AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP). These tool calls are the agent's syscalls: privileged operations with side effects on shared state, yet today's safety enforcement lives entirely in
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.19635v2 Announce Type: replace-cross Abstract: While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in real-time applications. Direct adaptation to streaming scenarios often leads to catastrophic inference performa
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.21241v2 Announce Type: replace-cross Abstract: Vision--Language--Action (VLA) models often use intermediate representations to connect multimodal inputs with continuous control, yet spatial guidance is often injected implicitly through latent features. We propose CorridorVLA, which predicts sparse spatial an
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.08442v4 Announce Type: replace-cross Abstract: Persistent memory in LLM agents creates an attack surface that production safety classifiers do not observe: the payload enters via RAG retrieval and persists across sessions via tool-mediated memory. We evaluate six defenses across four architectural layers aga
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.12569v2 Announce Type: replace-cross Abstract: Global navigation satellite system (GNSS) interference poses a serious threat to reliable positioning, especially in indoor and multipath-rich environments where source localization is highly challenging. In this paper, we formulate GNSS interference localizatio
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.25475v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A practical remedy is to
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.06510v3 Announce Type: replace-cross Abstract: Conventional HPC holds that native hardware FP64 is the irreducible foundation of scientific computing. On AI-optimized GPUs of the NVIDIA B300 generation and beyond, native FP64 throughput has collapsed to ~1.3 TFLOPS even as FP8 tensor throughput has grown to
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.22574v2 Announce Type: replace-cross Abstract: While synthetic data generation resolves the manual labeling bottleneck in computer vision, minimizing the syn-to-real domain gap requires optimizing rendering variables. This paper presents a systematic study analyzing the impact of lighting configurations and
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.23327v2 Announce Type: replace-cross Abstract: Video editing has become essential in digital media creation, yet existing automated systems are restricted to short segment processing and domain-specific tasks. They face two critical limitations: i) inability to handle diverse video comprehension and editing
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
LeRobot v0.6.0: Imagine, Evaluate, Improve
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Run AI workloads on any cloud, store on Hugging Face: zero-egress storage with SkyPilot
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
See how Australian Payments Plus uses ChatGPT Enterprise and Codex to move faster through payments complexity. AP+ saves time, improves quality, and keeps human judgment central.
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from openai.com.
What's changed Added a "Dynamic workflow size" setting in /config for controlling how large Claude generally makes dynamic workflows (small/medium/large agent counts) - an advisory guideline, not an enforced cap Added workflow.run_id and workflow.name OpenTelemetry attributes to telemetry emitted by workflow-spawned ag
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Changes since 1.2.7 release(langgraph): 1.2.8 ( #8292 ) fix: delta channel bug with updateState on fresh thread will force snapshot instead of stub checkpoint ( #8290 ) chore(deps): bump the minor-and-patch group in /libs/langgraph with 8 updates ( #8255 ) chore(deps): bump websockets from 15.0.1 to 16.0 in /libs/langg
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
API or pricing changes from huggingface.co can materially affect production costs and integration plans.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Changes since langchain-mistralai==1.1.5 release(mistralai): 1.1.6 ( #38684 ) feat(mistralai): surface citation metadata from chat responses ( #37008 ) chore(model-profiles): refresh model profile data ( #38663 ) chore: bump vcrpy from 8.1.1 to 8.2.1 in /libs/partners/mistralai ( #38302 ) chore: bump langsmith from 0.8
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Changes since langchain==1.3.10 release(langchain): 1.3.11 ( #38377 ) fix(langchain,openai): only set strict=True on tools for OpenAI-compatible models in ProviderStrategy ( #38370 ) chore: bump pydantic-settings from 2.12.0 to 2.14.2 in /libs/langchain_v1 ( #38279 ) chore: bump vcrpy from 8.1.1 to 8.2.1 in /libs/langc
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Changes since langchain-openrouter==0.2.5 release(openrouter): 0.2.6 ( #38681 ) fix(openrouter): support default_headers for custom HTTP header injection ( #36582 ) chore(model-profiles): refresh model profile data ( #38663 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
What's changed Claude Sonnet 5 sessions no longer use the mid-conversation system role for harness reminders
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
arXiv:2604.25421v3 Announce Type: replace-cross Abstract: Federated fine-tuning provides a practical route to adapt large language models (LLMs) on edge devices without centralizing private data. However, in mobile deployments, the training wall-clock is often dominated by straggler-limited uplink communication under h
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01394v1 Announce Type: new Abstract: We present Wiola, a fully original Small Language Model (SLM) architecture built from first principles, sharing no structural lineage with any existing model family including GPT, LLaMA, Mistral, or Falcon. Wiola introduces five independently novel components: (i) Spiral
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01584v1 Announce Type: new Abstract: Large language models have recently been explored for scientific hypothesis generation, but most prior work relies on unstructured literature and free-form textual claims. We present a pipeline for Earth observation that grounds hypothesis generation directly in the NASA
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01595v1 Announce Type: new Abstract: As the scale and complexity of cloud-based AI systems continue to escalate, ensuring service reliability through rapid fault detection and adaptive recovery has become a critical challenge. While existing approaches integrate Large Language Models (LLMs) for semantic unde
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01740v1 Announce Type: new Abstract: Public LLM leaderboards optimise for global average performance and do not capture the specific cognitive demands of financial-services work: a model that leads on MMLU-Pro may underperform on document-grounded compliance reasoning, and a coding leader may handle multi-tu
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01766v1 Announce Type: new Abstract: LLM agents are increasingly used to translate natural language into 3D scenes in a procedural way, but existing systems focus on static output. Dynamic 4D scenes from text alone, in which liquids flow, particles emit, rigid bodies cascade, and articulated mechanisms move
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01239v1 Announce Type: cross Abstract: Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable. We identify and test a central structural mechanism: BPE tokenization fragments safety-critical words into sub-word pieces, and the three public alignment datase
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01258v1 Announce Type: cross Abstract: The rapid advancement of Artificial Intelligence (AI) has been accompanied by significant increases in computational and environmental costs, driven by large-scale investments in AI infrastructure, hardware, and software. In particular, graphics cards have become centra
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01303v1 Announce Type: cross Abstract: Presentation Attack Detection (PAD) serves as a crucial safeguard for face recognition systems against presentation attacks such as printed photos, replayed videos, and 3D masks. Despite significant progress, existing PAD models still struggle to generalize across unsee
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01395v1 Announce Type: cross Abstract: At the heart of human visual perception lies the ability to maintain a continuous and coherent understanding of the external world. By integrating observations with accumulated experience, the human visual system can continuously adapt to variations in both the target a
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01418v1 Announce Type: cross Abstract: Organizations rolling out agentic command line tools like Anthropic's Claude Code and GitHub's Copilot CLI need to know who will try them, who will keep using them, and whether the tools produce enough output to justify their cost. At organizational scale, token spend c
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01431v1 Announce Type: cross Abstract: We introduce ISOSCI, a benchmark of isomorphic cross-domain science problem pairs that separates reasoning ability from domain knowledge retrieval in LLM evaluation. Each pair shares identical logical structure but requires different domain-specific knowledge, enabling
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01586v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) have recently advanced robotic manipulation, yet the effects of different robot-data pre-training paradigms remain difficult to compare because existing models often differ in architecture, data, action space, and evaluation protocol
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01702v1 Announce Type: cross Abstract: Recently, speech classification methods have gained widespread adoption in intelligent gadgets. Current study indicates that backdoor attacks provide a substantial security concern to these models, underscoring the pressing necessity to investigate additional potential
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01751v1 Announce Type: cross Abstract: Existing medical video benchmarks primarily evaluate whether a model produces the correct answer, but rarely assess whether it answers at the right time. In real clinical settings, AI systems must decide not only what to predict, but also when to answer, defer judgment
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01854v1 Announce Type: cross Abstract: Can a platform tell, before deployment, whether an open-weight checkpoint has had its refusal mechanism stripped? Runtime guards cannot: they score generations, not the artifact.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01897v1 Announce Type: cross Abstract: We introduce Rank-Then-Act (RTA), a framework for learning control policies from expert video demonstrations without environment rewards. RTA trains a Vision-Language Model (VLM) offline as a progress-based ordinal scorer, using a Group Relative Policy Optimization (GRP
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01951v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly consulted on contested scientific questions, raising the concern that they will sycophantically retreat from established consensus when a user signals doubt -- drifting toward a false balance that treats settled science as o
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01973v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly applied in medical tasks such as pathology description, report generation, and visual question answering. Medical Image Quality Assessment (MIQA) supports diagnostic accuracy and patient safety by determining whether images
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01984v1 Announce Type: cross Abstract: Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation. This study compares nine lightweight CNN model packages across CIFAR-10, CIFAR-100, and Tiny
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02371v1 Announce Type: cross Abstract: Over 285 million people worldwide live with a visual impairment, for whom everyday tasks such as avoiding obstacles, locating personal belongings, recognizing familiar faces, or handling cash remain persistent obstacles to personal autonomy. Existing assistive applicati
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.02469v1 Announce Type: cross Abstract: Software tests and code evolve together: a code change should be followed by new or updated tests that record the new software behavior. Yet existing test generation and update benchmarks often isolate the test from the code change, and rely on static metadata that does
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.20459v2 Announce Type: replace Abstract: Can AI systems trained on the existing scientific record forecast the advances that will follow? We introduce PreScience, a dataset and benchmark for scientific forecasting built around 98K recent AI research papers, together with companion papers covering author publ
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.08169v2 Announce Type: replace Abstract: Alignment in LLMs is more brittle than commonly assumed: misalignment can be induced by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors are encoded as linear structur
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.23965v3 Announce Type: replace Abstract: Large Language Models (LLMs) achieve strong performance on logical reasoning benchmarks, yet their reliability remains uncertain. Existing evaluations rely on static benchmarks, which fail to assess robustness under logically equivalent transformations and often overe
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.27898v2 Announce Type: replace Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential. However, reported benchmark scores often jointly reflect model capability and the implementation choices each benchmark is packaged with, making cross
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2506.09105v3 Announce Type: replace-cross Abstract: We present MetaTT, a Tensor Train (TT) adapter framework for fine-tuning of pre-trained transformers. MetaTT enables flexible and parameter-efficient model adaptation by using a single shared TT to factorize transformer sub-modules.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2508.16674v2 Announce Type: replace-cross Abstract: Medical report understanding from real-world document images is essential for generating patient-facing explanations and enabling structured information exchange in clinical systems. Existing VLMs and LLMs have shown strong performance on document understanding
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.26283v4 Announce Type: replace-cross Abstract: High-precision medical diagnosis relies not only on static imaging features but also on the implicit diagnostic memory experts instantly invoke during image interpretation. We pinpoint a fundamental cognitive misalignment in medical VLMs caused by discrete token
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.11357v2 Announce Type: replace-cross Abstract: With the growing demand for on-device LLM inference, edge SoCs increasingly integrate NPUs to improve performance and energy efficiency under tight power and thermal budgets. However, practical LLM deployment on current client NPUs remains difficult: widely used
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.18293v2 Announce Type: replace-cross Abstract: Thanks to rapid developments in generative AI, we are in the midst of a paradigm shift that may change how we interact with computers forever. We have observed a growth in the use of natural language prompts to build applications and coding infrastructures witho
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.24661v3 Announce Type: replace Abstract: Despite remarkable progress on reasoning benchmarks, current LLM evaluation practice remains anchored to final-answer correctness, providing limited insight into how models reason, how reliably they behave under contextual variation, or how efficiently they reach conc
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00001v1 Announce Type: new Abstract: Most approaches to AI alignment treat human preferences as fixed targets to be inferred and optimized. This assumption conflicts with extensive empirical evidence showing that preferences are layered, dynamic, and constructed through interaction--particularly with adaptiv
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00334v1 Announce Type: new Abstract: Autonomous agents, whether LLM-driven software agents or robotic physical agents, face a common class of failure modes when operating without continuous human oversight: safety violations from unverified actions, behavioral instability from unconstrained loops, and contin
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00457v1 Announce Type: new Abstract: Embodied agents operating in the real world require multi-scale reasoning and knowledge adaptation as conditions change. We identify two challenges in applying Mixture of Experts (MoE) to this setting: routing lacks an explicit notion of scale, preventing targeted updates
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00642v1 Announce Type: new Abstract: Reinforcement learning has proven to be a valuable tool in the creation of advanced AI and robotic systems, contributing to everything from game playing to robotics to foundation models. Through trial-and-error, these AI systems typically learn one, near-optimal behavior
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00924v1 Announce Type: new Abstract: Accelerating materials discovery requires AI systems that can generate scientifically valid hypotheses through multi-step, domain-grounded reasoning. Standard large language models often produce fluent but weakly traceable responses to open-ended materials design problems
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01188v1 Announce Type: new Abstract: In autonomous laboratories, AI agents suggest the next batch of experiments to do. However, planning and executing those tasks taking full advantage of the available resources is a completely different question.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01224v1 Announce Type: new Abstract: Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge--a capacity known in cognitive science as metamemory. We bring this perspective to LLMs by treating memory management as a trainable skill.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2511.18050v1 Announce Type: cross Abstract: Diffusion transformers have recently delivered strong text-to-image generation around 1K resolution, but we show that extending them to native 4K across diverse aspect ratios exposes a tightly coupled failure mode spanning positional encoding, VAE compression, and optim
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00006v1 Announce Type: cross Abstract: Beckmann & Butlin's (2026) ontological framework for the LLM individuation problem inherits an unargued cross-regime co-reference assumption from the persona-vectors literature: that the same direction picks out the same content under prompt-conditioning, gradient-desce
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00008v1 Announce Type: cross Abstract: Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when target schemas are large and complex. In such cases, including the full schema in the prompt increases cost and latency, risks lost-in-the-middle performance de
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00013v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are widely used in institutional question answering settings where responses must be grounded in authoritative documentation (Gao et al., 2023). In entity-dense domains where relevant information is distributed across heterog
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00016v1 Announce Type: cross Abstract: Information localization within massive repositories is a cornerstone of agentic LLM systems. While synthetic data-driven optimization has proven successful in training LLMs, little attention has been paid to optimizing the agent's working environment (the repository it
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00220v1 Announce Type: cross Abstract: Artificial intelligence (AI) systems are routinely modified after deployment through retraining and changes in their environments. These transformations raise a metaphysical question: under what conditions does an AI system remain the same system over time or across dep
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00247v1 Announce Type: cross Abstract: Large audio-language models (LALMs) frequently hallucinate by overriding acoustic evidence with language priors. While contrastive decoding (CD) offers training-free mitigation, existing methods rely on blunt perturbations like masking or noise, leaving structured audio
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00374v1 Announce Type: cross Abstract: Composed Image Retrieval (CIR) retrieves a target image from a reference image and a textual modification. While supervised CIR relies on costly triplets, Zero-Shot CIR (ZS-CIR) alleviates this reliance through proxy tasks trained on image-text pairs.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00397v1 Announce Type: cross Abstract: Understanding how complex cognitive functions are organized within artificial systems is central to interpreting large language models (LLMs) and relating them to biological cognition. Yet although LLMs exhibit broad cognitive-like behaviours, it remains unclear whether
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00442v1 Announce Type: cross Abstract: Reinforcement learning (RL) for quadruped locomotion commonly depends on fixed, hand-crafted, and Markovian reward functions that limit both interpretability of learned policies and lack explicit control over gait behaviors. We introduce a framework where distinct gaits
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00444v1 Announce Type: cross Abstract: Spatiotemporal motion planning, especially in multi-robot settings, requires robots to reason about collision-free regions that change over time, which is challenging in continuous spaces when feasible regions are transient and geometrically constrained. We present an a
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00501v1 Announce Type: cross Abstract: We present BaseRT, a native Metal inference runtime for large language models (LLMs) on Apple Silicon, and report the highest inference throughput on this hardware to date. Existing runtimes, including llama.cpp and MLX-based frameworks, incur overhead from abstractions
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00661v1 Announce Type: cross Abstract: Explanations for emotion classifiers are usually produced post hoc, with no guarantee that they reflect the computation behind the label. We present an explication interface for event-based emotion analysis.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00860v1 Announce Type: cross Abstract: Millimeter-wave (mmWave) beam alignment plays a critical role in next-generation wireless systems, yet its efficient implementation remains challenging. Meta-learning and transfer learning have been explored to enable deep learning-based beam prediction models to rapidl
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00918v1 Announce Type: cross Abstract: Although large language models (LLMs) have demonstrated impressive creative fiction generation, they struggle to maintain narrative consistency and coherent plot lines in long-form stories. In this work, we introduce a unified framework for long-form narrative generatio
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00926v1 Announce Type: cross Abstract: Generalizing machine learning models to environments that differ from their training distribution remains a critical hurdle, particularly when data from the target domain is entirely or partially unavailable. We propose Generative Meta-Learning with Human Feedback (GMHF
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.00989v1 Announce Type: cross Abstract: Semantic trajectory analysis has recently emerged as an approach for modeling human movement by capturing implicit patterns and behaviors through semantic information (e.g., visitors' profiles and goals) beyond raw spatial paths to better understand why people move in c
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01034v1 Announce Type: cross Abstract: Large language model (LLM)-based conversational agents (CAs) are now ubiquitous, creating new opportunities for AI-mediated behavior change. Their capacity to project nuanced personalities and adopt diverse metaphorical roles raises a design question: how should an agen
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01131v1 Announce Type: cross Abstract: Autonomous scientific discovery systems offer the potential to accelerate research by automating the process of hypothesis generation and validation. However, current systems operate within constrained search spaces or require predefined research questions, limiting the
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2607.01136v1 Announce Type: cross Abstract: Agent skills package reusable operational knowledge for Large Language Model (LLM) agents, yet as they grow in scope, they become dependency-bearing artifacts whose identities, versions, and provenance remain implicit. This opacity already causes duplicated dependencies
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2511.04500v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as decision-making agents in high-stakes domains and as imitators of human behavior in the social and behavioral sciences. Yet how closely LLMs mirror human decision-making remains poorly understood.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.03137v2 Announce Type: replace Abstract: LLM-based multi-agent simulation offers a promising way to study social interaction, deliberation, and collective opinion dynamics. However, many existing dialogue simulation frameworks represent interaction mainly as observable turn exchange or aggregated outputs, le
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2407.10887v4 Announce Type: replace-cross Abstract: Growing concerns over the theft and misuse of Large Language Models (LLMs) underscore the need for effective fingerprinting to link a model to its original version and detect misuse. We define five essential properties for a successful fingerprint: Transparency
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2503.13445v3 Announce Type: replace-cross Abstract: When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans. But are these explanations faithful, i.e.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2512.04988v2 Announce Type: replace-cross Abstract: Emerging agentic marketplaces provide the economic infrastructure for matching and coordinating the large amounts of AI agents used in agentic swarms. Unlike human workers, AI agents can operate on multiple jobs simultaneously, acquire skills rapidly, and labor
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.13059v2 Announce Type: replace-cross Abstract: Cost-per-click (CPC) in paid search is an auction-generated outcome shaped by a competitive landscape that is only partially observable from any single advertiser's history. From 1.66 billion Google Ads log records for a concentrated car-rental market (2021-2023
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.11430v2 Announce Type: replace-cross Abstract: AI agents that pay for resources via the x402 protocol embed payment metadata - resource URLs, descriptions, and reason strings - in every HTTP payment request. This metadata is transmitted to the payment server and to the centralised facilitator API before any
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.12243v2 Announce Type: replace-cross Abstract: Identifying promising research directions in fast-moving subareas is one of the most cognitively expensive tasks in modern AI research. Existing LLM-driven scientific discovery systems are typically limited to one-shot prompting on static literature snapshots an
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.13695v2 Announce Type: replace-cross Abstract: Mineral prospectivity modelling (MPM) underpins exploration economics, yet most operational pipelines reduce to data-driven classifiers trained on shallow surface proxies. Such models are blind to the subsurface physics that actually localises ore: heat advectio
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.25375v2 Announce Type: replace-cross Abstract: With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud. Although prior work has explored vision-language model (VLM)-based synthetic image detection, these evaluations typically c
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
GitHub is committed to empowering the developer community by helping organizations recognize and address the risks of secret leaks wherever they happen. We believe every enterprise should know the moment...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Enterprise administrators can now set model to auto in the enterprise managed-settings.json to make Copilot auto model selection the default for new conversations. Add auto to .github-private/.github/copilot/managed-settings.json in your source...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
0.115.1 (2026-07-01) Full Changelog: v0.115.0...v0.115.1 Chores api: remove some nonfunctional types from the SDKs ( 5e7c431 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
In June, we announced that we are retiring GitHub Models and closed it to new customers. We’re now sharing the timeline for the next step: GitHub Models will be fully...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
GitHub Enterprise Cloud customers can configure AI standards through a managed-settings.json file maintained in a .github-private repository in a selected organization. This allows the enterprise to define new governance and...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Secret scanning now runs validity checks on Asana, IBM, and MessageBird secrets so you can tell whether a leaked credential is still active. Validity checks added These patterns now support...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Claude Code v2.1.198 makes Claude in Chrome generally available, adds notification hooks for background agents, ships a new /dataviz skill, adds Claude Platform on AWS as a Gateway upstream, and fixes retry, auth-refresh, worktree, task-state, and agent-team reliability issues.
This is a workflow and reliability release, not a cosmetic patch. Teams using Claude Code get better long-running agent ergonomics, fewer transient-failure dead ends, cleaner background-task signaling, and a more practical path to AWS-hosted or multi-provider...
The Microsoft C++ Language Server is now available as a plugin on the Copilot Plugins marketplace. It includes a new built-in setup skill that helps automate project setup, making it...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Hermes Agent v0.18.0 is a builder-facing release with first-class Mixture-of-Agents presets, verification-backed completion contracts, /learn skill distillation, /journey memory timelines, background subagent fan-out, desktop coding projects, scale-to-zero gateway controls, and a broad security hardening pass.
This is a practical agent-platform release, not just a version bump. Teams building or operating coding agents get stronger evaluation loops, more observable multi-model orchestration, safer automation defaults, and better long-running deployment ergonomics...
Kimi K2.7 Code, an open-weight model, is now generally available in GitHub Copilot. This is the first open-weight model offered as a selectable option in the Copilot model picker, giving...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Collage of: 3 people looking at an Android phone, Android icons, two Android phones, and the text "Device enrolled"
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Copilot vision is now generally available. You can attach images and PDFs directly to your chat prompts so Copilot can reason about what it sees alongside your code.
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
You can now set AI credit session limits in Copilot CLI and the GitHub Copilot SDK to cap the amount an agent spends in a session. This is especially useful...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
The image shows the new Maps New Zealand feature
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Mem0 Pi Agent Plugin (v0.1.3) New Features: Guaranteed retrieval: Memories relevant to each prompt are now prefetched and injected as a block before the agent runs, so context no longer depends on the agent remembering to search. Context injection is on by default; set contextInjection: false to disable.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Mem0 OpenClaw Plugin (v1.0.14) Improvements: Sharper tool descriptions: Every memory tool ( memory_search , memory_get , memory_list , memory_add , memory_update , memory_delete ) now states what it does and when to use it. memory_search nudges proactive, multi-hop retrieval; memory_add nudges proactive saves; and the
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Mem0 OpenCode Plugin (v0.2.1) Improvements: Sharper tool descriptions: Every memory tool ( get_memories , get_memory , update_memory , delete_memory , delete_all_memories , delete_entities , list_entities , get_event_status ) now states what it does and when to use it. search_memories nudges proactive, multi-hop retrie
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Mem0 Node CLI (v0.2.10) Bug Fixes: entity delete : Keep every deleted entity in the result output instead of only the last one ( #5970 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Mem0 Python CLI (v0.2.9) Bug Fixes: entity delete : Keep every deleted entity in the result output instead of only the last one ( #5936 ) Output formatters: Handle null memory fields in the output formatters instead of erroring ( #5957 ) Config: Reject invalid integer config values with a clean error instead of a trace
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Mem0 Node SDK (v3.0.13) Bug Fixes: Embeddings: Guard against an embed_batch count mismatch in the OpenAI and Azure OpenAI embedders ( #5966 ) LLMs: Handle empty Google chat candidates without crashing ( #5817 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Mem0 Python SDK (v2.0.11) Bug Fixes: Embeddings: Guard against an embed_batch count mismatch in the OpenAI and Azure OpenAI embedders ( #5966 ) Memory: Re-raise LLM extraction failures instead of silently returning [] ( #5878 ) Vector Stores: Normalize vectors for the cosine distance strategy in FAISS ( #5960 ) Securit
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Browser tools for GitHub Copilot in VS Code are now generally available. Agents can now drive a real browser, navigate live web apps, and feed what they find back into...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Google, the New York Jobs CEO Council and Urban Assembly hosted an AI summit for 150 education and industry leaders.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
GitHub Copilot auto model selection now routes to the best model for your task in Copilot CLI, using utilization and model health metrics for a high quality, reliable, and token-efficient...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
arXiv:2606.23032v3 Announce Type: replace Abstract: Finance Agent v2 (by Vals AI) has emerged as the reference benchmark for evaluating both Anthropic Claude and OpenAI ChatGPT frontier language models on financial tasks. However, it narrowly deals with periodic reporting from publicly traded companies (SEC 10-K and 10
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.27876v2 Announce Type: replace-cross Abstract: Spatial intelligence is essential for low-altitude unmanned aerial vehicle (UAV) perception, collaboration, and navigation. However, existing UAV benchmarks often emphasize image-level recognition, single-view understanding, or narrow answer formats, leaving 3D
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30931v1 Announce Type: new Abstract: The LLM Jury, a Panel of LLM Evaluators (PoLL) reporting consensus scores, has become a practical alternative to single-judge LLM evaluation, yet its statistical behavior remains poorly understood. We formalize the LLM Jury under the Huber contamination model and show tha
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30975v1 Announce Type: new Abstract: Adaptive agents are usually judged by what they do, but an agent can appear stable while the internal effort required to keep it stable is increasing. This hidden regulatory burden matters for artificial agents operating under noise, delay, or changing demands: two system
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31046v1 Announce Type: new Abstract: Artificial life has explored life-like behavior on many computational substrates, but mostly in researcher-designed closed worlds. We argue that large language model (LLM) agents, with persistent memory, tool use, network access, and payment, now make it possible to move
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31131v1 Announce Type: new Abstract: To ensure safe on-road behavior, pre-deployment testing and failure discovery of Autonomous Driving Systems (ADS) is crucial. Present day simulation based testing methods focus largely on mathematical models for efficient search of optimal scenarios, assuming a fixed scen
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31179v1 Announce Type: new Abstract: As AI agents become increasingly capable of complex, long-horizon reasoning, rigorous and holistic evaluation is essential for measuring progress toward real-world healthcare applications. We introduce HealthAgentBench, a suite of 54 agentic healthcare tasks across 7 cate
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31325v1 Announce Type: new Abstract: We present HistoriQA-ThirdRepublic: a French-language dataset of multi-hop historical questions derived from parliamentary debates and newspapers of the French Third Republic. Designed in collaboration with a historian, the corpus captures complex reasoning patterns typic
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31334v1 Announce Type: new Abstract: Joint OFDM-RIS optimization for 6G is a mixed-integer nonlinear programming (MINLP) problem covering sum-rate maximization, energy efficiency, max-min fairness, and peak-to-average power ratio (PAPR)-constrained objectives. Seventy-eight joint OFDM-RIS optimization works
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31404v1 Announce Type: new Abstract: Human swarm intelligence demonstrates remarkable collective accuracy but faces scalability constraints in cost, coordination, and time. We investigate whether large language models (LLMs) can approximate swarm intelligence effects through artificial swarms, addressing a c
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31470v1 Announce Type: new Abstract: Cloud virtual machines are often overprovisioned, creating avoidable cost and operational inefficiency. We present CLOUDADV, an interactive engineer-facing advisory system for cloud instance sizing under workload drift.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31495v1 Announce Type: new Abstract: We study a single idea across two settings: that a prediction-error signal, computed by a small predictor over the latent space of a frozen encoder, can serve both as a gate on plasticity and as a substrate for metacognition. In the first system, a non-parametric episodic
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31543v1 Announce Type: new Abstract: Large language models can produce fluent, internally coherent reasoning traces for abstract reasoning tasks while still being confidently wrong - making selection among candidates, not just generation, the central challenge. I present a solver for ARC-AGI-2, a few-shot vi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31616v1 Announce Type: new Abstract: Medical Artificial Intelligence (AI) is widely expected to transform clinical practice, yet the decision-making processes of many Machine Learning (ML) models remain opaque. Explainability has been advanced as a partial remedy to clarify why AI generates predictions, part
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31648v1 Announce Type: new Abstract: We present LuckyStar 111B, a 111B-parameter hybrid reasoning model developed through a collaboration between Cohere and LG CNS for Korean-English enterprise agents under practical memory and serving constraints. The model trains from Cohere's fully post-trained Command A
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30646v1 Announce Type: cross Abstract: Speech recruits the same executive, attentional, and working memory processes underlying instrumental activities of daily living, or IADLs, providing a non-invasive proxy for cognitive assessment. Yet most speech-based dementia detection systems depend on transcription
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30668v1 Announce Type: cross Abstract: What happens when LLM agents operate with no context outside a turn, minimal prompting, and simple tools? Inspired by swarm engineering, we give collectives of three agents the ability to send messages and manipulate a shared actively decaying text store, introducing ev
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30675v1 Announce Type: cross Abstract: Early detection of dementia through speech analysis offers a non-invasive screening alternative, but capturing both acoustic and linguistic biomarkers remains challenging. We propose a multimodal framework leveraging Whisper for dual-purpose extraction: acoustic represe
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30680v1 Announce Type: cross Abstract: Truck-drone delivery is an emerging last-mile logistics mode combining the long-haul capacity of trucks with the flexible service capability of drones. In locker-based operations, smart lockers serve not only as temporary parcel storage facilities but also as automated
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30688v1 Announce Type: cross Abstract: Symmetry provides a quantum neural network structure, but on its own it does not keep the network trainable once noise is present. We ask which physical quantity decides whether the gradients of an equivariant circuit survive decoherence, and we answer with a compact tr
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30697v1 Announce Type: cross Abstract: Current operating systems expose interfaces optimized for human users but not for AI agents. Humans benefit from pixels, icons, windows, visual grouping, mouse movement, and keyboard shortcuts; AI agents instead need compact semantic state, grounded actions, and reliabl
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30702v1 Announce Type: cross Abstract: Structured tabular data dominates clinical medicine, yet existing benchmarks fail to reflect real-world properties like complex survey sampling, demographic oversampling, and subgroup fairness. We introduce the NHANES Accelerometry Cardiometabolic Benchmark, derived fro
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30704v1 Announce Type: cross Abstract: Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutions often lack the structural consistency needed for reliable deployment. Workflows that encode recurring algorithmic patterns at the task level provide a principled frame
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30705v1 Announce Type: cross Abstract: Deterministic few-step generation succeeds on continuous image latents but collapses to incoherent text on continuous text latents, and we show the cause is geometric rather than a training or scaling deficiency: a smooth, regularity-limited deterministic map cannot res
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30989v1 Announce Type: cross Abstract: Warning: This paper contains several toxic and offensive statements. While reasoning generally improves fairness in recent large language models (LLMs), failures persist.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31048v1 Announce Type: cross Abstract: This paper investigates knowledge distillation from a large reasoning model (DeepSeek-R1) to a compact student model (Qwen2.5-7B). Using historical problems from the John O'Bryan Mathematics Competition at Northern Kentucky University (2011-2025), we build a Chain-of-Th
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31154v1 Announce Type: cross Abstract: Creating and editing slides is a rich, multimodal activity that is ubiquitous in professional and educational settings, making it an ideal testbed for real-world computer-use agents. Microsoft PowerPoint is among the most widely adopted and feature-rich environments for
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31156v1 Announce Type: cross Abstract: RAG systems retrieve documents optimized for answering one query at a time. Yet enterprise users arrive with sessions, that is, coherent episodes of related questions that span semantically distant parts of the knowledge base.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31158v1 Announce Type: cross Abstract: The quest for intuitive and natural human-robot interaction (HRI) remains a significant challenge in robotics. Traditional methods often rely on rigid, pre-programmed commands that limit the robot's expressiveness and adaptability.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31198v1 Announce Type: cross Abstract: Real-time video segmentation of the prostate in Transrectal Ultrasound (TRUS) is essential for image-guided interventions. While conventional 2D methods suffer from inter-frame inconsistencies by disregarding temporal context, 3D architectures incur prohibitive latency.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31259v1 Announce Type: cross Abstract: Diffusion-based text-to-audio (TTA) models achieve impressive synthesis quality but suffer from high inference latency due to iterative multi-step denoising. Existing one-step approaches alleviate this issue but still rely on paired text--audio data during distillation.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31268v1 Announce Type: cross Abstract: The growing demand for privacy-preserving data sharing has positioned synthetic data generation as a critical component of responsible AI workflows. Despite notable advances in generative modeling, existing solutions often lack integration of adaptive generation strateg
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31377v1 Announce Type: cross Abstract: Reinforcement learning for long-horizon robotic manipulation is often limited by sparse and delayed rewards, while manually designing dense shaping signals is costly and brittle to changes in environments and object configurations. This work proposes Stage-Transition De
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31683v1 Announce Type: cross Abstract: Diffusion models have emerged as a dominant paradigm in generative modeling, enabling high-fidelity sampling from complex data distributions. Despite impressive capabilities, controlling diffusion models to produce outputs aligned with user intent remains an open challe
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31742v1 Announce Type: cross Abstract: Explainable AI (XAI) methods have demonstrated significant success in recent years at identifying relevant features in input data that drive deep learning model decisions, enhancing interpretability for users. However, the potential of XAI beyond providing model transpa
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31844v1 Announce Type: cross Abstract: A local-to-global context mismatch arises when autoregressive traffic simulators trained on ego-centric driving logs are deployed in globally observable closed-loop environments. In such logs, the ego vehicle has rich local observations, while surrounding agents are onl
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31981v1 Announce Type: cross Abstract: Creating photorealistic, animatable 3D human avatars from monocular images still largely depends on Linear Blend Skinning (LBS) and parametric body models, which constrain expressivity and often introduce artifacts due to imperfect fitting. We propose LUNA, an LBS-free
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.31991v1 Announce Type: cross Abstract: The tendency of large generative models to memorize training data makes sample verification critical for privacy auditing and copyright enforcement. Current membership (MIA) and dataset inference (DI) attacks often rely on one-shot generations, which yield weak signals
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.32032v1 Announce Type: cross Abstract: Metacognition is a critical component of intelligence that describes the ability to monitor and regulate one's own cognitive processes. Yet LLMs exhibit systemic deficiencies in key metacognitive faculties: they hallucinate with high confidence, fail to recognize knowle
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2601.14171v2 Announce Type: replace Abstract: Writing effective rebuttals is a high-stakes task that demands more than linguistic fluency, as it requires precise alignment between reviewer intent and manuscript details. Current solutions typically treat this as a direct-to-text generation problem, suffering from
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.29965v2 Announce Type: replace Abstract: The development of temporal extensions of Answer Set Programming (ASP) has led to the emergence of non-monotonic linear-time (TEL), dynamic (DEL), and metric (MEL) temporal equilibrium logics. However, the inherent rigidity of highly optimized ASP systems often hinder
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.02863v2 Announce Type: replace Abstract: AI-Driven Research Systems (ADRS) -- systems coupling LLMs with automated evaluation to discover algorithms, proofs, and designs -- are being optimized and adopted across domains, but the tools to analyze them have not kept pace. ADRS performance depends on component
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.03741v2 Announce Type: replace Abstract: Long-horizon reasoning requires a system to commit to medium-horizon intent without becoming rigid: re-plan too often and computation never coheres into multi-step structure; commit too long and the plan goes stale. We study this stability-adaptivity tradeoff in the l
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.23672v2 Announce Type: replace Abstract: This paper presents our algorithmic innovations for the NVIDIA Nemotron Model Reasoning Challenge, focusing on Bit Manipulation Puzzles. In this task, the objective is to discover a hidden logical rule transforming input binary strings to outputs, then apply it to uns
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2507.11061v3 Announce Type: replace-cross Abstract: Recent advances in 3D neural representations and instance-level editing models have enabled the efficient creation of high-quality 3D content. However, achieving precise local 3D edits remains challenging, especially for Gaussian Splatting, due to inconsistent m
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2511.17442v3 Announce Type: replace-cross Abstract: Foundation Models (FMs) are increasingly integrated into remote sensing (RS) pipelines. These models include unimodal vision encoders and multimodal architectures.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2601.23088v2 Announce Type: replace-cross Abstract: Semantic caching has emerged as a pivotal technique for scaling LLM applications, widely adopted by major providers including AWS and Microsoft. By utilizing semantic embedding vectors as cache keys, this mechanism effectively minimizes latency and redundant com
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.03981v2 Announce Type: replace-cross Abstract: Credit exposure in Decentralized Finance (DeFi) is often implicit and token-mediated, creating a dense web of inter-protocol dependencies. Thus, a shock to one token may result in significant and uncontrolled contagion effects.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.16428v2 Announce Type: replace-cross Abstract: Fine-tuning Large Language Models (LLMs) has become essential for domain adaptation, but its memory-intensive property exceeds the capabilities of most GPUs. To address this challenge and democratize LLM fine-tuning, we present SlideFormer, a novel system design
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.09735v2 Announce Type: replace-cross Abstract: Static-graph LLM decoders provide predictable launches, fixed tensor shapes, and low submission overhead, but online decoding exposes highly irregular KV-cache behavior: request lengths differ, EOS events arrive asynchronously, and logical histories fragment ove
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.11030v2 Announce Type: replace-cross Abstract: Closed-loop tool-using agents are increasingly evaluated in executable web, code, and micro-task environments, but benchmark reports often conflate workloads, action-generating drivers, and the evidence admitted for systems-facing claims. We present an executabl
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
@mastra/[email protected]
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
@mastra/[email protected]
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Hugging Face and Cerebras bring Gemma 4 to real-time voice AI
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Example spark task "Monitor interior design internships for this summer"
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
0.115.0 (2026-06-30) Full Changelog: v0.114.0...v0.115.0 Features api: add support for Managed Agents event delta streaming, agent overrides, reverse pagination, vault credential injection scoping, and agent and deployment webhook events ( 8c23f7e )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from huggingface.co.
What's changed Introducing Claude Sonnet 5: now the default model in Claude Code, with a native 1M-token context window and promotional pricing of $2/$10 per Mtok through August 31. Update to version 2.1.197 for access.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
0.114.0 (2026-06-30) Full Changelog: v0.113.0...v0.114.0 Features api: add support for claude-sonnet-5 ( b893033 ) Bug Fixes agent_toolset: allow absolute paths that resolve inside workdir ( #121 ) ( 0105529 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Claude Sonnet 5 is Anthropic’s latest Sonnet-class model, now available in GitHub Copilot. It brings strong coding performance to everyday development and agentic workflows, giving developers a new Sonnet-class option...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
You can now use branch rulesets to block pull requests from merging when test coverage drops below thresholds you set. You can set a minimum coverage percentage, a maximum allowed...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
You can now scan and navigate release pages more easily with a dedicated sidebar table of contents. We also updated release metadata placement for a more consistent layout so it’s...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Enterprises can now manage their dependencies’ licenses at scale with sophisticated, ruleset-based checks that enforce a centralized policy. Open source license compliance is in public preview, letting you block noncompliant...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
A collage of a landscape, a Google search for "sustainability", windmills, and Google Maps
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Today, JetBrains and GitHub are announcing a deeper integration between JetBrains AI Assistant and GitHub Copilot. Millions of developers already rely on the GitHub Copilot plugin as their AI pair...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
mp4 showing a title card reading "Build with our generative media models"
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
Why Specialization Is Inevitable
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Dependabot will no longer attempt to infer .npmrc configuration for npm private registries. Previously, Dependabot tried to reconstruct .npmrc contents from lockfile resolved URLs, but incorrect lockfile URLs, lockfile format...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Starting August 25, 2026, GitHub will introduce a data retention policy for closed Dependabot security alerts. This policy gives you a clear commitment for how long your alert data stays...
Teams giving assistants data or tool access should review the security failure mode described by github.blog.
As part of our ongoing commitment to protect our users and ensure responsible use of our platform, the Notifications team will soon introduce access restrictions to several public API endpoints...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
New OpenAI Signals data shows how ChatGPT adoption is growing globally, with users increasing usage, exploring more capabilities, and driving growth across regions and languages.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
Enterprise admins can now set a cost center user-level budget: one per-user AI credit budget on a cost center that applies to every individual in it. As membership changes, the...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
arXiv:2606.18379v2 Announce Type: replace-cross Abstract: Graph-based retrieval at billion-node scale requires jointly solving three tightly coupled problems -- graph construction, representation learning, and real-time serving -- yet existing work addresses each in isolation. We present RankGraph-2, a framework deploy
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.14202v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have advanced Automatic Heuristic Design (AHD) by enabling heuristic generation through reasoning and code synthesis. In LLM-based AHD, the LLM reasons about algorithm design and generates executable heuristic code.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.20523v2 Announce Type: replace-cross Abstract: Multimodal foundation models have advanced rapidly thanks to large optical benchmarks, but comparable resources for synthetic aperture radar (SAR) remain limited. Existing SAR--optical datasets largely rely on low-resolution, intensity-only Ground Range Detected
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28374v1 Announce Type: new Abstract: LLM agents are increasingly improved without weight updates by evolving a natural-language artifact, such as reflections, workflows, playbooks, cheatsheets, or optimized prompts, that conditions a frozen policy. Such methods are typically reported as wins on the single be
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29069v1 Announce Type: new Abstract: Concept-based Explainable AI (C-XAI) seeks human-understandable explanations grounded in semantic concepts, yet validation is limited by the scarcity of fine-grained concept annotations. We evaluate whether mid-scale Multimodal Large Language Models (MLLMs) can perform lo
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29661v1 Announce Type: new Abstract: Top AI forecasting systems are approaching superforecaster-level accuracy on future world events, but still rely primarily on off-the-shelf LLMs combined with forecasting-specific context gathering and scaffolding. We study how to improve this recipe through ensembling: g
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29771v1 Announce Type: new Abstract: LLM agents are increasingly cast as autonomous portfolio managers, and benchmarks have moved from financial question-answering to sequential trading. Yet most still rank agents by returns over a fixed window -- a weak proxy, since a period's return is dominated by the mar
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29799v1 Announce Type: new Abstract: This project introduces the CRISTAL Method (Coherent Reliable Intentional Synthesis of Truthful Analysis Logic), a neurosymbolic framework for automating complex analysis workflows, with fundamental investment analysis as a primary use case. This domain poses major challe
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30294v1 Announce Type: new Abstract: Live product demonstrations are a recurring, high-cost activity in software organizations: a human presenter must select features, dispatch the corresponding interactions on a running application, narrate them coherently, and answer questions in real time. Existing automa
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28331v1 Announce Type: cross Abstract: The widespread deployment of generative artificial intelligence (AI) models has raised serious concerns about the proliferation of AI-generated content. This has led to a surge of interest in, and demand for, reliable tracking and detection mechanisms for content that i
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28347v1 Announce Type: cross Abstract: Contemporary AI safety spans pre-training interventions, post-training alignment, deployment-time controls, monitoring, and red-teaming. These methods are necessary, but they primarily certify snapshots of system behavior.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28362v1 Announce Type: cross Abstract: Systematic reviews and meta-analyses (SR/MA) remain the gold standard for evidence synthesis, yet completing one typically requires 67 weeks and substantial expert effort. Recent large language model (LLM) systems have demonstrated strong performance on individual SR ph
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28363v1 Announce Type: cross Abstract: Objective: To describe the architecture and design rationale of meta-pipe, an open-source large language model (LLM)-agent pipeline that integrates the complete systematic review and meta-analysis (SR/MA) workflow -- from literature search through statistical analysis
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28376v1 Announce Type: cross Abstract: Long-horizon large language model (LLM) agents accumulate interaction trajectories that quickly exceed any practical prompt budget, and existing memory methods either truncate aggressively and lose non-local evidence or retain boilerplate that degrades decision quality.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28380v1 Announce Type: cross Abstract: The intricate structures of biological neural networks largely emerge during development, guided by a comparatively compressed blueprint encoded in the genome. The connectivity that emerges from this decoding process is rich in structure, and already equips the organism
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28387v1 Announce Type: cross Abstract: Enterprise text-to-SQL systems often fail before SQL is generated: the model receives the wrong schema context. Modern warehouses contain thousands of tables, abbreviated columns, informal metrics, hidden join conventions, and permission boundaries that are not captured
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28391v1 Announce Type: cross Abstract: The wide use of Convolutional Neural Networks (CNN) in numerous domains and real-world classification applications is justified by their high precision and automation speed, helping users concentrate on higher-expertise tasks. To better understand the models and avoid b
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28445v1 Announce Type: cross Abstract: Early detection of dementia enables timely intervention, and reflecting cognitive impairment, spontaneous speech offers a non-invasive screening modality. Conventional approaches often focus on a single representational dimension -- such as acoustic descriptors, pause m
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28533v1 Announce Type: cross Abstract: Sequence learning has emerged as the promising paradigm in recommendation systems, surpassing traditional Deep Learning Recommendation Models (DLRM) by capturing the temporal nuances of user behavior. However, current state-of-the-art architectures operate under a limit
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28644v1 Announce Type: cross Abstract: Parameter settings in evolutionary algorithms and metaheuristics are important because such parameter values can influence the performance of algorithms under evaluation. For a given algorithm, there are many different numerical experiments to show that the algorithm ca
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28676v1 Announce Type: cross Abstract: Predicting the risk of distant metastasis from primary tumor tissue histology is a critical yet challenging task in computational pathology. Multiple Instance Learning (MIL) approaches can attend to subdomains in tumor regions that harbor features of metastatic cancer p
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28856v1 Announce Type: cross Abstract: While AI holds the potential to revolutionize space life sciences, realizing this promise is contingent upon the systematic restructuring of heterogeneous spaceflight biological data into machine-actionable, AI-ready forms. Even though open access principles support hum
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28881v1 Announce Type: cross Abstract: Predicting student performance and characterizing metacognitive calibration are essential for personalization in intelligent tutoring systems. Prior research treats performance prediction, calibration error calculation, and variance decomposition as separate pipelines
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28896v1 Announce Type: cross Abstract: Synthetic aperture radar (SAR) data augmentation is important for improving the generalization of data-driven SAR interpretation models, yet practical augmentation workflows are often hindered by heterogeneous dataset formats, task-dependent metadata requirements, diver
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28980v1 Announce Type: cross Abstract: Ovarian cancer is frequently diagnosed at an advanced stage, making preoperative contrast-enhanced computed tomography (CT) central to staging and surgical planning; yet the scarcity of annotated imaging data, compounded by privacy regulations, limits the development of
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29038v1 Announce Type: cross Abstract: Metric aggregation divergence (MAD) is the silent inconsistency that arises when distinct pipeline stages in an agent-based model coupled with a multi-objective evolutionary algorithm (ABM+MOEA) independently re-implement how an outcome metric is extracted from simulati
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29073v1 Announce Type: cross Abstract: Model Context Protocol (MCP)-style ecosystems give language-model applications a practical connection layer for tools, resources, prompts, and transports. As agents move from connection to execution, security decisions often remain split across clients, servers, prompts
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29441v1 Announce Type: cross Abstract: Inference-time safety methods for large language models have proliferated, yet no systematic comparison exists. We evaluate five defense paradigms (no defense, static steering, CAST, AlphaSteer, probe-gated) across seven instruction-tuned models (7-31B) and five attack
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29459v1 Announce Type: cross Abstract: Inverse design of metal-organic frameworks (MOFs) requires searching a combinatorially vast space where property labels are expensive and most machine-learning models reveal little about why a structure succeeds. We introduce LLM4MOF, a closed-loop framework in which la
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29577v1 Announce Type: cross Abstract: Positron Emission Tomography (PET) reveals brain metabolism and is clinically central to neurodegenerative disease assessment, yet existing 3D brain foundation models treat PET as generic volumetric data, missing the structured regional metabolic information that distin
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29582v1 Announce Type: cross Abstract: Bilevel optimization has become an influential and widely adopted framework for addressing hierarchical optimization problems in machine learning, providing an effective approach to modeling the interaction between two levels of optimization, with applications such as h
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29648v1 Announce Type: cross Abstract: Different retrievers, including lexical, semantic, and multimodal approaches, provide highly complementary strengths for multimodal document understanding, yet most systems combine them through fixed pipelines that cannot adapt to the demands of individual reasoning ste
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29778v1 Announce Type: cross Abstract: Long-term conversational agents need to remember and query cross-session, multi-typed information with complex correlations. Existing agent memory systems rely on heterogeneous vector and graph databases, which fragment memory information and cause high cross-database I
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29797v1 Announce Type: cross Abstract: Machine learning network intrusion detection systems (IDS) rely on aggregate flow statistics that discard distributional structure, while established entropy measures require raw packet sequences unavailable in pre-aggregated flow datasets. We propose Multi-Level Distri
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29820v1 Announce Type: cross Abstract: In complex continuous-control reinforcement learning tasks, multimodal optimal actions often coincide with uncertain, multimodal return distributions, making reliable value estimation and multimodal exploration challenging. Existing value estimation methods using unimod
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29823v1 Announce Type: cross Abstract: The database community has repeatedly advanced the state of the art by recognizing that new workloads demand new system architectures. We argue that long-horizon agentic tasks -- code generation, scientific discovery, hardware design -- are such a workload.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.29966v1 Announce Type: cross Abstract: Quantum computing provides a powerful paradigm for representing and transforming high-dimensional information through superposition, entanglement, and measurement-induced nonlinear features. While current quantum hardware is not yet practical for direct large-scale visi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30209v1 Announce Type: cross Abstract: We present a multi center breast fine needle aspiration cytology (FNAC) dataset designed for patch wise classification using C1 to C5 reporting labels. The prospective dataset includes 321 patients and 470 whole-slide images (WSIs) collected from participating tertiary
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30304v1 Announce Type: cross Abstract: This paper presents preliminary findings from a UKRI-funded Metascience project comparing three LLM-based approaches, GPT-4o, Mistral, and a bespoke algorithm, DSIT-Taxonomies, for extracting and classifying research entities from funding proposals. Our project "Trackin
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30317v1 Announce Type: cross Abstract: The Model Context Protocol (MCP), introduced by Anthropic in November 2024, defines a standardized interface for connecting large language models (LLMs) to external tools, data sources, and services. Within months of release, hundreds of community-built MCP servers appe
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30410v1 Announce Type: cross Abstract: Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry. Research communities across disciplines are increasingly evaluating tabular foundation models on diverse datasets and tasks.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30473v1 Announce Type: cross Abstract: We study retrieval over catalogs of structured metadata, where each record is a small schema whose fields answer different kinds of query. Embedding a record with a text encoder first serializes its fields into a string, which forces a choice of field order.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30549v1 Announce Type: cross Abstract: AI code completion tools, such as Github Copilot, provide students with code suggestions to help them write programs. However, recent qualitative studies suggest that students fail to critically evaluate these suggestions.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30576v1 Announce Type: cross Abstract: Cross-view object geo-localization (CVOGL) aims to locate a target object from a query view (e.g., ground or drone) within a geo-tagged reference image (e.g., satellite). Existing approaches heavily rely on 2D appearance matching and are constrained by limited datasets
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30609v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionaries exposes fundamental challenges. Systematic studies reveal pervasive feature splitting t
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.30642v1 Announce Type: cross Abstract: Full-length song generation must preserve coherence and musicality, render detailed vocal and accompaniment acoustics, and follow lyrics and prompts. Existing language model-based systems face a structural trade-off: mixed-token modeling preserves vocal-instrument coord
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.13792v2 Announce Type: replace Abstract: Artificial intelligence built on large foundation models has transformed language understanding, computer vision, and reasoning, yet these systems remain isolated and cannot readily share their capabilities. Coordinating the complementary strengths of independently de
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.01189v2 Announce Type: replace Abstract: Clinical AI adoption is hindered by the black-box/grey-box nature of high-performing models, which lack the ontological grounding and narrative transparency required for professional-level explainability. We present NEURON, a neuro-symbolic system designed to enhance
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.10044v2 Announce Type: replace Abstract: World model has emerged as a powerful paradigm in artificial intelligence, enabling agents to represent their environments, predict future states, and evaluate possible actions before acting. However, existing world model approaches have largely been developed for dom
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2101.05993v2 Announce Type: replace-cross Abstract: Selecting an appropriate classification algorithm for a given data set remains a challenging problem in data mining and machine learning. Existing algorithm recommendation models are typically trained with individual learners and rely on only one type of meta-fe
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2506.08795v2 Announce Type: replace-cross Abstract: Limb loss affects millions globally, impairing physical function and reducing quality of life. Most traditional surface electromyographic (sEMG) and semi-autonomous methods require users to generate myoelectric signals for each control, imposing physically and m
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2508.17117v3 Announce Type: replace-cross Abstract: Existing plant-disease datasets target classification and detection, leaving vision-language models unable to support interactive, reasoning-based diagnosis. To address this, we present PlantExpertVQA, a large-scale visual question answering (VQA) dataset design
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2510.09278v2 Announce Type: replace-cross Abstract: Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2510.12957v4 Announce Type: replace-cross Abstract: We treat the internals of generative models as mechanistic objects rather than black boxes. We introduce \textbf{Attribution Graphs} (AGs), which extend GradCAM++ to circuit-level representations, and \textbf{Causal Probing}, a do-calculus intervention method fo
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2511.05852v4 Announce Type: replace-cross Abstract: Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs). Meanwhile, fine-tuning remains the default operation for adapting LLMs to new domains and tasks.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2512.16455v4 Announce Type: replace-cross Abstract: The rapid growth of Artificial Intelligence and Machine Learning in scientific research has highlighted a gap between industry-standard MLOps tools and platforms, and the unique requirements of modern and Open Science, particularly regarding the FAIR (Findable
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2601.13534v3 Announce Type: replace-cross Abstract: Time series generation (TSG) is widely used across domains, yet most existing methods assume regular sampling and fixed output resolutions. These assumptions are often violated in practice, where observations are irregular and sparse, while downstream applicatio
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2601.20334v2 Announce Type: replace-cross Abstract: Robotic manipulation has increasingly adopted vision-language-action (VLA) models, which achieve strong performance but typically require task-specific demonstrations and fine-tuning, and often generalize poorly under domain shift. We investigate whether general
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.02320v4 Announce Type: replace-cross Abstract: Molecular function is largely determined by structure. Accurately aligning molecular structure with natural language is therefore essential for enabling large language models (LLMs) to reason about downstream chemical tasks.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.15727v2 Announce Type: replace-cross Abstract: Visual analogy learning enables image editing via demonstration rather than textual description, allowing users to specify complex transformations difficult to articulate in words. Given a triplet $\{\mathbf{a}$, $\mathbf{a}'$, $\mathbf{b}\}$, the goal is to gen
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.16634v2 Announce Type: replace-cross Abstract: The rare-event sampling problem has long been the central limiting factor in molecular dynamics (MD), especially in biomolecular simulation. Recently, diffusion models such as BioEmu have emerged as powerful equilibrium samplers that generate independent samples
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.13326v2 Announce Type: replace-cross Abstract: Multimodal Transformers often produce predictions without clarifying how different modalities jointly support a decision. Most existing multimodal explainable AI (MXAI) methods extend unimodal saliency to multimodal backbones, highlighting important tokens or pa
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.02371v2 Announce Type: replace-cross Abstract: Visual long-document understanding is critical for enterprise, legal, and scientific applications, yet the best performing open recipes have not explored reasoning, a capability which has driven leaps in math and code performance. We introduce a synthetic data p
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.23354v3 Announce Type: replace-cross Abstract: Neural networks can be trained to learn task-relevant representations from data. Understanding how these networks make decisions falls within the Explainable AI (XAI) domain.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.09708v2 Announce Type: replace-cross Abstract: We present Metal-Sci, a 10-task benchmark of scientific Apple Silicon Metal compute kernels spanning six optimization regimes (stencils, all-pairs in $n$-body problems, multi-field Boltzmann, neighbor-list molecular dynamics, multi-kernel PDE, FFT). Each task sh
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.31603v2 Announce Type: replace-cross Abstract: Connector-based video unified models have demonstrated strong capability in instruction-grounded video synthesis, but integrating a large high-fidelity generator into the unified training loop is computationally prohibitive, limiting achievable visual quality. W
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.06748v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) reduces but does not eliminate hallucination in large language models. Existing detection methods rely on flat similarity between generated answers and retrieved passages, ignoring structural relationships among evidence piec
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.15129v2 Announce Type: replace-cross Abstract: Color fundus photography (CFP) is the mainstay of large-scale retinal screening, but its diagnostic capacity is limited by the lack of depth-resolved structure, which optical coherence tomography (OCT) provides yet is less accessible at population scale. We pres
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
Changes since 1.2.6 release(langgraph): 1.2.7 ( #8223 ) fix(langgraph): snapshot DeltaChannel overwrite supersteps ( #8125 ) fix(langgraph): Make Overwrite survive JSON roundtrips ( #8127 ) chore(deps): bump redis in /libs/langgraph ( #7976 ) chore(deps): bump langsmith from 0.8.0 to 0.8.18 in /libs/langgraph ( #8176 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Featuring Every Eval Ever Results on Hugging Face Model Pages
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
OpenAI engineers used large-scale core dump analysis to debug rare infrastructure crashes, uncovering both a hardware fault and a long-standing software bug.
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from openai.com.
Introducing GeneBench-Pro, a new benchmark testing AI performance in genomics, biology, and scientific research using complex, real-world datasets.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from openai.com.
Anthropic's Claude Code v2.1.196 adds org-level default model selection, clickable file attachments in chat, safer MCP approval behavior for repo-committed .mcp.json servers, better background-session recovery after restarts, and a streaming watchdog enabled by default.
This is a meaningful Claude Code workflow release, not just a version bump: it changes model governance for teams, tightens MCP safety around self-approved servers, and improves recovery for long-running agent sessions on real developer machines.
Changes since langchain-openrouter==0.2.4 release(openrouter): 0.2.5 ( #38553 ) fix(openrouter): deduplicate repeated finish metadata ( #38552 ) fix(openrouter): strip Responses reasoning IDs ( #38383 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
DiScoFormer: One transformer for density and score, across distributions
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Personal Intelligence makes the Gemini app feel tailored to you. With your permission, it pulls from Google tools like Gmail, Google Photos, YouTube and Search to provid...
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
Claude Opus 4.8 (fast mode) is now rolling out in preview on GitHub Copilot. Fast mode delivers significantly faster output token speeds while maintaining the same intelligence as Claude Opus...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Repository admins can now restrict issue creation to collaborators with write access. This gives you more control over who can open issues and helps reduce unwanted issue creation, while keeping...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
An illustration depicting a full-stack AI infrastructure against a dark background
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Google Meet's "Take notes for me" feature is available to Google AI Pro and Ultra subscribers in select languages.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
0.113.0 (2026-06-29) Full Changelog: v0.112.0...v0.113.0 Features api: add support for 20260318 web fetch and support tools ( 88dbfb1 ) Bug Fixes async count_tokens missing output_format/output_config merge block ( #162 ) ( 122c958 ) Chores api: accept user profile ID's when counting tokens ( 0b4d17a ) docs: updates to
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
New features will help prove how YouTube brand campaigns are driving the results advertisers care about.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
A new OpenAI report maps how AI could reshape jobs across the EU, highlighting which occupations may face automation, growth, or workflow changes.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
arXiv:2606.23698v2 Announce Type: replace-cross Abstract: NVIDIA's Blackwell Ultra (B300) cuts FP64 vector throughput to ~1.3 TFLOPS per GPU, roughly 30x below B200 and well below the level at which bandwidth-limited FP64 workloads stay memory-bound. The Ozaki Scheme II framework recovers FP64-equivalent throughput by
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.14612v5 Announce Type: replace-cross Abstract: Answering natural-language questions over multi-hour audio requires both event recognition and temporal grounding. Current large audio-language models perform well on short clips, but are limited by context length, query-time cost, and weak temporal localization
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26964v2 Announce Type: replace Abstract: As embodied AI and world models increasingly operate in dynamic 3D environments, visual perception must move beyond passively interpreting given observations toward actively deciding what to observe. We study this problem through camera planning in dynamic 3D story wo
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.27826v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly deployed as embodied planners in egocentric environments, where task success requires not only achieving instructed goals but also acting in socially appropriate ways. While explicit goals may render certain action
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28076v1 Announce Type: new Abstract: Knowledge graph question answering (KGQA) aims to answer natural-language questions by reasoning over structured facts. Existing multi-hop KGQA methods mainly rely on topic-centered expansion, which faces two key challenges: the search space rapidly grows with noisy mixed
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28270v1 Announce Type: new Abstract: The transition from static chat bots to autonomous agents--equipped with persistent memory, tool-use protocols, and multi-agent collaboration--has fundamentally expanded the AI threat landscape. Current defense mechanisms, such as perimeter security and training-time alig
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2601.16956v1 Announce Type: cross Abstract: The rapid growth of Large Transformer-based models, specifically Large Language Models (LLMs), now scaling to trillions of parameters, has necessitated training across thousands of GPUs using complex hybrid parallelism strategies (e.g., data, tensor, and pipeline parall
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.27598v1 Announce Type: cross Abstract: Ultra-fine entity typing (UFET) assigns highly specific types to entity mentions, but current approaches struggle with types in the long tail. We hypothesize that a key limitation is the reliance on sentence-level context, since disambiguating evidence is often spread a
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.27599v1 Announce Type: cross Abstract: While many explainable AI (XAI) methods have been proposed, most are not designed for time-series forecasting models and often rely on the implicit assumption that timestamp features are independent. This assumption ignores the fundamental property of temporal dependenc
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.27657v1 Announce Type: cross Abstract: Obesity is a global health crisis associated with metabolic disorders such as type 2 diabetes and cardiovascular disease. This study employed single-cell RNA sequencing to reconstruct the developmental trajectory of human adipocytes from adipose tissue samples.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.27667v1 Announce Type: cross Abstract: Artificial intelligence is transforming biodiversity monitoring by enabling automated analysis of ecological imagery collected from camera traps, drones, satellites, underwater platforms, and other sensing systems. These tools can expand the scale and speed of conservat
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.27694v1 Announce Type: cross Abstract: Randomized Smoothing (RS) provides rigorous robustness guarantees for neural networks without architectural constraints, yet its adoption is limited by extreme computational costs. Standard RS requires tens of thousands of model evaluations per input and forces practiti
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.27881v1 Announce Type: cross Abstract: Temporal variation poses a unique challenge for named entity recognition (NER) in historical texts, where entities drift in surface form and salience across time. While language models (LMs) have made progress in various NLP tasks, their ability to reason about temporal
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.27973v1 Announce Type: cross Abstract: Speech-based cognitive impairment detection offers a noninvasive, accessible alternative to costly biomarker assays, yet transformer-based models remain clinically uninterpretable. We propose a multi-stage explainability framework that translates black-box transformer p
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28268v1 Announce Type: cross Abstract: Test-time adaptation (TTA) has emerged as a promising paradigm for mitigating distribution shifts in deep models. However, existing TTA approaches for anomaly segmentation remain limited by their reliance on pixel-level heuristics, such as confidence thresholding or ent
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.28277v1 Announce Type: cross Abstract: Artificial intelligence is driving a revolution in scientific discovery, accelerating everything from hypothesis generation to mathematical theorem proving. However, this rapid acceleration is creating a systemic challenge: traditional human peer review cannot scale to
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2603.00374v2 Announce Type: replace Abstract: Offline learning of strategies takes data efficiency to its extreme by restricting algorithms to a fixed dataset of state-action trajectories. We consider the problem in a mixed-motive multiagent setting, where the goal is to solve a game under the offline learning co
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2510.10271v2 Announce Type: replace-cross Abstract: Unlike regular tokens derived from existing text corpora, special tokens are artificially created to annotate structured conversations during the fine-tuning process of Large Language Models (LLMs). Serving as metadata of training data, these tokens play a cruci
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.13072v2 Announce Type: replace-cross Abstract: OpenClaw-style personal assistants extend LLM agents from isolated tool use to open-ended, stateful, and personalized software environments. Evaluating these assistants is fundamentally a fidelity problem: benchmarks must be faithful both to the distribution of
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.22160v2 Announce Type: replace-cross Abstract: Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation. Humans robustly detect and segment moving entities that constitute independently moveable chunks of matter, whether observing sparse
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.30719v2 Announce Type: replace-cross Abstract: We study when large language models (LLMs) can serve as effective black-box policy optimizers for reinforcement learning (RL) tasks, i.e., when can we replace classical RL algorithms with an LLM? We explore this question by introducing Prompted Policy Optimizati
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
HP Inc. scales its OpenAI Frontier partnership to deploy AI across customer experiences, software development, and enterprise operations.
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from openai.com.
Mem0's Node SDK v3.0.12 adds LiteLLM proxy routing, a MiniMax provider, memory-expiration controls, PGVector URI/SSL options, and an undici upgrade to remediate CVE-2026-12151.
Teams using Mem0 as an agent memory layer can now route through LiteLLM without a custom wrapper, pick up a documented CVE fix in the HTTP stack, and simplify PGVector deployment configuration in the same release.
Mem0 Python SDK (v2.0.10) New Features: Client: Expose expiration_date on MemoryClient.update() and AsyncMemoryClient.update() - callers can now set or clear a memory's expiration date; None is preserved and forwarded to the API ( #5874 ) Bug Fixes: Memory (OSS): Apply remove_code_blocks() to the LangChain path in asyn
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
arXiv:2606.26173v1 Announce Type: new Abstract: Recent work shows that Large Language Models (LLMs) can act as semantic mutation operators for the evolutionary discovery of programs and proofs. Most current applications focus on static coding benchmarks.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26203v1 Announce Type: new Abstract: As AI agent protocols proliferate, the governance structures shaping their interoperability standards remain empirically underexamined. We introduce an LLM-powered comparative pipeline for large-scale governance discourse analysis, integrating automated annotation, neural
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26348v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can process diverse inputs, e.g., text, images, audio, and video, and generate textual responses. While their capabilities have advanced rapidly, evaluation of such models has not kept pace.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26502v1 Announce Type: new Abstract: Large reasoning models (LRMs) take longer on harder problems, just as humans do. This surface similarity hides an opposite pattern within items.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26728v1 Announce Type: new Abstract: Scientific discovery is fundamentally an optimization problem, defined by a vast "state space" of theories and experiments, and an evaluation criterion based on quality, novelty, and validity. Large language models (LLMs) have enabled automated exploration of this space
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
A new arXiv paper argues that agent memory needs more than retrieval. It introduces the loop-drift benchmark and an EVAF LoRA-based consolidation method that preserved goal persistence and post-unload recovery better than retrieval alone, while using only 2-3 parametric writes per 200 events across GPT-2, TinyLlama, an
Most agent memory stacks can recall facts but still lose goals after long loops or context resets. This paper gives builders a concrete benchmark for that failure mode and a lightweight consolidation pattern to test when retrieval alone stops being enough.
arXiv:2606.26857v1 Announce Type: new Abstract: The interpretation phase of life cycle assessment often lacks structured mechanisms for translating quantified improvement opportunities addressing environmental hotspots into actionable strategic pathways under technological, social, and policy uncertainty. To overcome t
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
A new arXiv paper proposes BINEVAL, which breaks LLM evaluation into atomic yes-or-no questions instead of opaque judge scores. In tests on SummEval, Topical-Chat, and QAGS, it matched or beat stronger LLM-judge baselines while producing question-level feedback that can also drive prompt improvement.
Teams using LLM judges usually get a score without a clear reason. BINEVAL turns evaluation into debuggable checks, which makes it easier to audit failing outputs, compare prompts, and plug evaluator feedback back into prompt or agent tuning loops.
arXiv:2606.27334v1 Announce Type: new Abstract: Digital twins have emerged as a promising paradigm for personalized healthcare, enabling modeling of individual behavior and health trajectories. In cognitive health, early detection of Mild Cognitive Impairment (MCI) remains challenging, where language and conversational
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26101v1 Announce Type: cross Abstract: Reliable evaluation of large language models should separate supported answering from unsupported guessing without conflating either with data contamination, prompt idiosyncrasy, or generic refusal behavior. We present a contamination-aware, multi-zone benchmark for mea
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26111v1 Announce Type: cross Abstract: Generative artificial intelligence (GenAI) has enabled users to synthesize music with text prompts, combining copyrighted lyrics, AI-composed melodies, and synthetic vocals that imitate real artists. This paper examines the legal and technical dimensions of AI-based mus
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26114v1 Announce Type: cross Abstract: We examine the structural transformation of creative industries under generative artificial intelligence, drawing on 374 primary sources spanning policy documents, industry data, creator surveys, and platform analytics. Beginning with the December 2024 release of OpenAI
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26116v1 Announce Type: cross Abstract: A brand whose customers use both ChatGPT and Claude for product recommendations faces a strategic choice: a single optimization playbook, or one per provider? Across 215 commercially-framed prompts in four measurement batches, the two providers disagree on which brands
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26117v1 Announce Type: cross Abstract: This paper introduces the Governance Inversion Hypothesis (GIH) to explain a growing paradox in artificial intelligence (AI) governance: under conditions of increasing regulatory expansion and technological complexity, organisations may become more formally governed whi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26118v1 Announce Type: cross Abstract: We work towards measuring both AI adoption and the capability of AI to perform discrete labor tasks across various occupations. To measure adoption, we develop an open-source economic index that uses publicly available user-LLM chat data and O*NET tasks to replicate stu
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26196v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have recently made remarkable progress in unifying vision-language understanding and reasoning, especially following the introduction of models such as OpenAI's O-series and DeepSeek's R-series, which have driven a paradigm shift
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
Lacuna turns machine-learning papers and scholarly metadata into a source-linked research map with web, markdown, and MCP interfaces. On LitSearch, Multi-XScience-CS/ML, and ScholarQA-CS-ML it outperformed OpenScholar, and its Lacuna Deep Research agent beat GPT-Researcher on ReportBench-ML citation quality and expert
Teams building research copilots or internal literature maps now have a concrete design pattern for turning papers into source-linked MCP knowledge that can answer questions, surface directions, and draft survey-style reports with stronger retrieval and...
arXiv:2606.26260v1 Announce Type: cross Abstract: In laser penetration welding, the assessment of penetration state and weld seam morphology plays a crucial role in determining the weld quality. This paper presents a comprehensive introduction of the innovative muti-task deep learning model that has the capability to p
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26290v1 Announce Type: cross Abstract: While parameter-efficient fine-tuning (PEFT) typically targets attention projectors, its efficacy for tasks requiring sequential state accumulation remains under-explored. We examine if PEFT for such tasks can benefit from state space model (SSMs) adapters, and if MLP b
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26327v1 Announce Type: cross Abstract: In actor-critic reinforcement learning, network architectures are typically manually designed. Automating this design is challenging because each candidate must be trained before evaluation, and the design space is open-ended.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26442v1 Announce Type: cross Abstract: We present AXLE (Axiom Lean Engine), a cloud service for Lean 4 proof manipulation, extraction, and verification. Recent progress in AI for mathematics -- reinforcement learning pipelines, agentic proving workflows, dataset curation -- demands Lean 4 tooling that scales
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26487v1 Announce Type: cross Abstract: Large language models (LLMs) are attractive for context-aware time series forecasting because they can integrate heterogeneous textual signals, yet their discrete, language-oriented tokenization and embedding interfaces are misaligned with continuous numerical values, o
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26559v1 Announce Type: cross Abstract: Earth observation satellite networks generate massive volumes of high-resolution imagery, whereas inter-satellite and downlink resources remain limited. In many time-sensitive missions, ground users require mission-relevant semantic information rather than a full raw-im
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26563v1 Announce Type: cross Abstract: Single-cell studies require analysts to convert raw measurements into specific biological claims through multi-step workflows and integration of metadata, assay context, and auxiliary evidence. Existing AI-biology benchmarks largely measure broad knowledge, executable w
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26764v1 Announce Type: cross Abstract: Developing robust artificial intelligence models for 4D (3D + time) medical imaging is constrained by limited annotated data, inter-device domain shifts, and privacy restrictions. To address this, we propose a 4D controllable generative framework for anatomically consis
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26866v1 Announce Type: cross Abstract: Third-party vendors, such as analytics platforms, cloud services, identity providers, and software suppliers, are increasingly embedded in digital service delivery. While these arrangements enable scale and specialization, they also move customer data and security-relev
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.26901v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) is increasingly used to document clinical encounters, yet its reliability in multilingual and demographically diverse Indian healthcare context remains largely unknown. In this study, we first conduct the systematic audit of ASR perfor
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.27180v1 Announce Type: cross Abstract: Sparse rewards are inherently challenging for reinforcement learning agents as they lack intermediate feedback to guide exploration and to correctly attribute the sparse success rewards to relevant parts of the trajectory. Naive reward shaping can induce reward hacking
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.27233v1 Announce Type: cross Abstract: We present a conceptual framework for analyzing dialogue in collaborative problem-solving contexts, with an emphasis on the emerging dynamics of human-AI and multi-agent collaboration. As intelligent systems become active agents capable of autonomous reasoning and strat
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.27251v1 Announce Type: cross Abstract: Building persistent embodied agents in unstructured environments demands unified orchestration of heterogeneous tools spanning both cyber (APIs, IoT) and physical (manipulation, navigation) domains, coupled with autonomous recovery from physical failures that inevitably
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.17554v3 Announce Type: replace Abstract: Frontier deep research agents (DRAs) are being deployed in enterprise workflows faster than they are being evaluated. Existing benchmarks measure factual recall, single-hop QA, or generic agentic skill, and miss the multi-document, decision-grade deliverables DRAs are
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.20657v2 Announce Type: replace Abstract: Post-training a frontier model is normally weeks of human work: proposing data and recipe changes, launching runs, reading evals, deciding what to keep. We report an autonomous system that runs this loop with no human in the loop, post-training a 30B Nemotron across f
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2508.16159v2 Announce Type: replace-cross Abstract: Meta-learning aims to uniformly sample homogeneous support-query pairs, characterized by the same categories and similar attributes, and extract useful inductive biases through identical network architectures. However, this identical network design results in ov
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2601.01701v2 Announce Type: replace-cross Abstract: Anomaly detection is increasingly becoming crucial for maintaining the safety, reliability, and efficiency of industrial systems. Recently, with the advent of digital twins and data-driven decision-making, several statistical and machine-learning methods have be
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2601.03388v3 Announce Type: replace-cross Abstract: Earlier research has shown that metaphors influence human decision-making, raising the question of whether metaphors also influence large language models (LLMs)' reasoning pathways, given that their training data contain a large number of metaphors. In this work
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.09234v2 Announce Type: replace-cross Abstract: The King Wen sequence of the I-Ching (c. 1000 BC) orders 64 hexagrams -- states of a six-dimensional binary space -- in a pattern that has puzzled scholars for three millennia.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.13755v2 Announce Type: replace-cross Abstract: We argue that aligning AI to aggregated human preferences is the wrong target. With current technology, one can train AIs to share the values of a Silicon Valley techno-optimist, a degrowth environmentalist, a national-conservative culture warrior, a single-part
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
What's changed Added CLAUDE_CODE_DISABLE_MOUSE_CLICKS to disable mouse click/drag/hover in fullscreen mode while keeping wheel scroll Fixed hook matchers with hyphenated identifiers (e.g. code-reviewer , mcp__brave-search ) accidentally substring-matching - they now exact-match.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Changes since langchain-anthropic==1.4.7 release(anthropic): 1.4.8 ( #38490 ) fix(anthropic): keep initial text on content_block_start ( #38442 ) chore: bump langgraph-checkpoint from 4.1.0 to 4.1.1 in /libs/partners/anthropic ( #38479 ) fix(core): add messages to bare raise ValueError calls ( #38158 )
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Building on the AI adoption phase cohorts added to the Copilot usage metrics API, organization and enterprise reports now report the total number of pull requests merged by each adoption...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
@mastra/[email protected]
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
@mastra/[email protected]
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
MAI-Code-1-Flash, Microsoft AI’s in-house coding model, is now generally available for GitHub Copilot Business and Copilot Enterprise, building on its recent expansion across Copilot surfaces. Purpose-built for coding and optimized...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
If you’ve got a faraway trip coming up, the Gemini app can help you avoid jetlag so you can make the most of your visit. Once you’ve given Gemini permission to access you...
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
GitHub Desktop 3.6 brings more of your day-to-day Git flow into one place with GitHub Copilot now powering commit authoring and merge conflict resolution, plus new Git worktree support. The...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
OpenAI previews GPT-5.6 Sol, a next-generation model with stronger capabilities in coding, science, and cybersecurity, paired with its most advanced safety stack.
Teams giving assistants data or tool access should review the security failure mode described by openai.com.
Changes since langchain-fireworks==1.4.2 release(fireworks): 1.4.3 chore: bump vcrpy from 8.1.1 to 8.2.1 in /libs/partners/fireworks ( #38314 ) chore: bump langsmith from 0.8.16 to 0.8.18 in /libs/partners/fireworks ( #38313 ) chore: bump langsmith from 0.8.14 to 0.8.16 in /libs/partners/fireworks ( #38235 ) chore: bum
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Run a vLLM Server on HF Jobs in One Command
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
What's changed Added autoMode.classifyAllShell setting to route all Bash/PowerShell commands through the auto-mode classifier instead of only arbitrary-code-execution patterns Added auto-mode denial reasons to the transcript, the denial toast, and /permissions recent denials Added claude_code.assistant_response OpenTel
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Copilot code review now uses the built-in file exploration tools available in the Copilot CLI and SDK, significantly improving review cost efficiency with no change to your existing workflow. If...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Enterprises can now control which plugins their users can install in GitHub Copilot CLI and VS Code. This setting is now available in public preview.
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Saved views for repository issues Repository Issues pages now support saved views, making it easier for teams to create and share filtered views of their issues. With saved views, anyone...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Organizations now have more control over who can use GitHub-hosted runners in Actions. Admins can now disable the standard labels for hosted runners such as ubuntu-latest, as well as add...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Google.org is providing a $5 million grant to scale Obrii, Ukraine’s national AI job platform. This contributes to Ukraine's AI adoption, following sustained investment ...
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
A graphic featuring the Gemini logo surrounded by icons representing educational tools, including Guided Learning, Study Notebooks, and NotebookLM, set against a background featuring a security shield and classroom imagery.
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from blog.google.
Job hunting can be a slog. But with a few Google AI tools, you can simplify the process from start to finish. Career Dreamer: The first step in landing a job is finding o...
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Colorful illustration of two happy parents with a smiling child and toddler.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
GitHub Actions now supports running steps concurrently using background. Previously, all steps in a workflow ran in sequence, with each step starting only after the previous step completed.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Which tokens does a hybrid model predict better?
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
npm now adds a temporary, preventive safeguard for high-impact accounts-those responsible for the registry’s most widely used packages-whenever it detects a sensitive account change, strengthening protection against account-takeover attacks. When...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
The latest announcements from Google for Education at ISTE 2026.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Our June Demand Gen Drop offers more ways to elevate campaign performance and engage new viewers on YouTube.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
We are announcing new funding at the 2026 ISTE conference to support two long-term partners.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
An abstract illustration of the Gemini interface on a tablet, surrounded by colorful 3D icons including a graduation cap, stylized people, and a four-pointed star.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
mp4 reading "Meet study notebooks in Gemini"
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
The Google Finance logo, surrounded by elements of the user interface
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
GitHub-hosted larger runners now support Red Hat Enterprise Linux (RHEL) 9 and RHEL 10 images in public preview, introduced in partnership with Red Hat. Organizations can use these RHEL images...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
GitHub Copilot for Jira is now generally available. Since launching the public preview in March 2026, we have shipped a series of enhancements based on your feedback, including model selection,...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
A woman holds plates. A Google Nest is on her table.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
We’re pleased to share that the UK will be one of the first markets to benefit from updates to Google Play’s business model, bringing lower fees and more choice to devel...
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
Cost attribution across your enterprise can now follow your team structure. You can add enterprise teams as resources in a cost center, and all usage incurred by team members is...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
The debate over AI governance is stuck in a false choice between over-regulation and no regulation. There is a middle way: A pragmatic, evidence-based approach that reco...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from blog.google.
A digital graphic collage on a clean white background with faint grey grid lines. In the center foreground sits a large, Google Gemini logo in vibrant red, blue, green, and
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
arXiv:2606.02800v4 Announce Type: replace-cross Abstract: We introduce Cosmos 3, a family of omnimodal world models designed to jointly process and generate language, image, video, audio, and action sequences within a unified mixture-of-transformers architecture. By supporting highly flexible input-output configuration
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24047v1 Announce Type: new Abstract: One of the significant mental health issues affecting female sex workers (FSWs) is mental disorders, especially depression. Exposure to violence, stigma, and economic hardship further increases their psychological risk.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24251v1 Announce Type: new Abstract: Large language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and self-preservation. As they are increasingly deployed in high-stakes settings, it is critical to reliably detect such behaviors to ensure safe and responsibl
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24391v1 Announce Type: new Abstract: We introduce Age of LLM, a turn-based 1v1 benchmark in which two LLMs face off on a 13x7 grid to destroy the enemy base. Three stressors are deliberate: fog of war, full diplomacy (messages, ceasefires, ultimatums; uranium kept secret), and a reliability dimension where e
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24470v1 Announce Type: new Abstract: A real-time agent for general computer use - with games as the most demanding case - must act within tens of milliseconds while still planning over seconds. These two regimes sit at opposite ends of the latency-quality tradeoff.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24589v1 Announce Type: new Abstract: Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real. We present AdversaBench, an end-to-end red-teaming pipeline that mutates seed prompts with five struct
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24622v1 Announce Type: new Abstract: Training safe Reinforcement Learning (RL) systems is inherently challenging, with no guarantee of avoiding unwanted behaviors. The most effective defenses against this are (i) transparency through explainability and (ii) alignment via human feedback.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24669v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential for planning and sequential decision-making, but prior work often relies on using them as direct controllers, which requires precise action generation and can be unreliable in practice. This paper proposes Latent Ac
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24839v1 Announce Type: new Abstract: Agentic data analysis systems produce rich outputs, including code, numerical results, and verbal diagnostics. This makes them more challenging to evaluate than single-turn LLM responses.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.23697v1 Announce Type: cross Abstract: Semantic segmentation of code written in a C-family language remains a challenging problem, due to the language's complex syntax, macro expansion, and irregular structural patterns. Existing chunking methods, such as fixed-sized windows, heuristic splitting, and syntax
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.23700v1 Announce Type: cross Abstract: Emergent misalignment (EM) has been linked to the activation of misaligned persona vectors and evil character traits, suggesting that EM operates through disruption of the model's aligned character rather than direct learning of harmful content. Motivated by this connec
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.23701v1 Announce Type: cross Abstract: Qualitative product feedback can reveal nuanced user experiences, but its implicit sentiment is difficult to measure. This paper presents a scalable and interpretable framework that uses large language models (LLMs) to quantify product desirability from such data.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.23758v2 Announce Type: cross Abstract: Domain generalization learns from multiple source domains to generalize to unseen target domains. However, it often neglects the realistic case of label mismatch between source and target.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.23759v1 Announce Type: cross Abstract: Verilog debugging remains one of the most time-consuming stages in digital circuit design. Recent advances in Large Language Models (LLMs) have enabled automated debugging; however, most existing approaches rely solely on test outputs and compiler feedback in an end-to
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.23853v1 Announce Type: cross Abstract: This paper studies strict majority reasoning in finite electorates using so-called $\textit{social decision frames}$: finite sets of voters equipped with distinguished families of coalitions interpreted as those voting blocs evaluated to form a strict majority. A cohere
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24062v1 Announce Type: cross Abstract: Financial time series forecasting presents structural challenges absent from standard benchmarks. Log-returns are non-stationary, exhibit exceptionally low signal-to-noise (SNR) ratios, and are governed by regime-dependent temporal dependencies.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24172v1 Announce Type: cross Abstract: More than a billion people communicate in Indic languages, yet the natural language processing infrastructure serving them remains fragmented and underdeveloped. The cause is structural: the field organizes its tools and benchmarks around individual languages or small s
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24206v1 Announce Type: cross Abstract: Recent breakthroughs in 3D generation have advanced notably with the development of text-to-image diffusion model. However, existing methods remain two practical challenges: (1) They primarily generate single 3D object, but struggle to generate multi-object compositiona
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24307v1 Announce Type: cross Abstract: Interactive music and live performance relies on real-time human expression, but modern generative music AI remains largely absent from this domain due to its prohibitive inference latency and offline rendering paradigm. To provide pioneer musicians with a novel medium
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24430v1 Announce Type: cross Abstract: Training of neural networks for histopathology classification tasks typically relies on data encoding into latent space, which reduces complexity and improves performance. There are several encoder networks available, either pretrained on general image datasets such as
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.24472v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have made rapid progress in generalist robot manipulation by harnessing semantic knowledge from pretrained vision-language backbones, but their visual tokens remain grounded in 2D image coordinates rather than the calibrated geometry
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2508.04460v2 Announce Type: replace Abstract: Large Reasoning Models (LRMs) can exhibit step-by-step reasoning, reflection, and backtracking, but these behaviors are often unregulated, leading to overthinking. As a result, LRMs continue generating redundant reasoning even after reaching high-confidence conclusion
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.07066v3 Announce Type: replace Abstract: Autonomous systems that build structures from natural-language instructions need reliable spatial reasoning, yet large language models (LLMs) make systematic coordinate errors when generating three-dimensional block placements. We present a neuro-symbolic pipeline bas
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.22974v2 Announce Type: replace Abstract: Recent work on preference elicitation in large language models (LLMs) has demonstrated that, when given a series of choices between two outcomes, LLMs reveal a coherent, model-specific utility structure. Notably, this structure often includes preferences that the mode
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2512.15067v4 Announce Type: replace-cross Abstract: The rapid growth in wireless infrastructure has increased the need to accurately estimate and forecast electromagnetic field (EMF) levels to ensure ongoing compliance, assess potential health impacts, and support efficient network planning. While existing studie
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.23967v2 Announce Type: replace-cross Abstract: In biological systems, sensing is not performed by the brain alone: the body deforms, vibrates, and filters external stimuli before they are transduced into neural signals. In engineered systems, this processing burden is placed largely on electronics and comput
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2605.26144v3 Announce Type: replace-cross Abstract: We present VISTA (VIsual Spec-To-App Benchmark), a benchmark for evaluating the end-to-end web-app generation capabilities of LLM-based agents. Unlike prior code generation benchmarks that focus on algorithmic tasks, VISTA targets realistic UI-centric developmen
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.12824v2 Announce Type: replace-cross Abstract: AI governance for medical imaging is formalizing: the 2026 ACR-SIIM Practice Parameter recommends local acceptance testing and ongoing drift monitoring, and the ACR Assess-AI registry monitors AI outputs using DICOM metadata for context. We argue that a necessar
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.13535v3 Announce Type: replace-cross Abstract: Particle physics collider experiments provide Rivet routines as part of the analysis preservation strategy for model-independent measurements. Rivet is a C++ toolkit that allow new theoretical models to be compared to the measurements, thus aiding the developmen
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.22314v2 Announce Type: replace-cross Abstract: Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attributing model predictions to input features by integrating gradients along a path from a baseline to the input. How
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
A new OpenAI research paper shows how AI agents are transforming work, enabling longer, more complex tasks and expanding productivity across roles.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
0.112.0 (2026-06-24) Full Changelog: v0.111.0...v0.112.0 Features client: add support for system.message streaming events ( 2450d59 ) Bug Fixes memory tool: create parent directories with the correct permissions ( #135 ) ( f2fc2a9 ) Chores api: add support for new refusal category ( 5ab533e ) api: add support for sendi
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
For a timely response to security incidents involving compromised accounts or stolen credentials, GitHub Enterprise owners can now use new “break-glass” capabilities to instantly revoke all credentials for a given...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Copilot Free and Student plans will now use Copilot auto model selection as the default and only model selection experience. Auto dynamically selects the best model for each task, removing...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModel
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
Gemini 3.5 logo on a blue background
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
What's changed Bug fixes and reliability improvements
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Mem0 Node SDK (v3.0.10) Memory (OSS): Guard against malformed image_url entries in parseVisionMessages to prevent crashes ( #5631 ) Memory (OSS): Return attributedTo from get() , search() , and getAll() ( #5675 ) Memory (OSS): Preserve message roles in the extraction input so assistant facts aren't attributed to the us
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Mem0 Python SDK (v2.0.8) New Features: Embeddings: Add native embed_batch to five embedders - LM Studio, Together, HuggingFace, Vertex AI, and Google GenAI - for batched embedding requests ( #5609 ) Bug Fixes: Core: Guard against malformed image_url entries in parse_vision_messages to prevent crashes ( #5631 ) Core: Re
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Mem0 Python CLI (v0.2.8) Security Telemetry no longer passes the Mem0 API key to its child process via command-line arguments. The context is now sent over stdin, so the key is no longer visible in the process list (ps, /proc//cmdline, Activity Monitor).
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Mem0 Node CLI (v0.2.9) Security Telemetry no longer passes the Mem0 API key to its child process via command-line arguments. The context is now sent over stdin, so the key is no longer visible in the process list (ps, /proc//cmdline, Activity Monitor).
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Illustration of a woman walking through an airport with a suitcase
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Bringing more control over your connectors
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
OpenAI and Broadcom introduce Jalapeño, a custom AI chip built for LLM inference to improve performance, efficiency, and scale across AI systems.
Builders should compare the release against their current model for capability, latency, cost, and deployment fit.
@mastra/[email protected]
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Introducing the FFASR Leaderboard: Benchmarking ASR in the Real World
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
What's changed Added sandbox.credentials setting to block sandboxed commands from reading credential files and secret environment variables Added org-configured model restrictions to the model picker, --model , /model , and ANTHROPIC_MODEL , with a "restricted by your organization's settings" message when a restricted
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Secret scanning now includes extended metadata for Replicate secrets, providing richer context for leaked credentials. Extended metadata support This pattern now includes extended metadata when detected, providing richer context about...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Photo of a waterside city with flood alerts on top
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from blog.google.
Repository-level REST APIs for Code Quality findings are now available in public preview, bringing API support closer to the functionality already available in the GitHub UI. Two new read-only endpoints...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
GPT-5 Pro helped solve a 3-year-old immunology mystery, offering insights into T cell behavior. The breakthrough could support cancer and autoimmune research.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
Image of various forms using autofill
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Dependabot can now read from private GitHub Packages registries without a personal access token. If a package has granted your repository access through “Manage Actions access” in the package settings,...
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
The redesigned terminal interface for GitHub Copilot CLI that we previewed at Microsoft Build 2026 is now generally available. You get a tabbed layout for working with GitHub directly from...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Bright, colorful illustration on a red background showing a blue/green/yellow ombre sun, palm trees, flip flops, sunglasses and shell
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Dependabot no longer supports Python version 3.9, which has reached its end-of-life. If you continue to use Python 3.9, there’s a risk that Dependabot will not create pull requests to...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
We're launching Meta Glasses with 26 styles across a range of colors, lenses, and frames, so there's a pair for just about any style.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
OpenAI helps build shared standards for advanced AI, supporting evaluation frameworks, safety practices, and global cooperation through the Appia Foundation.
Policy or safety changes from openai.com can alter adoption, compliance, or audit assumptions.
Build real agentic apps using CUGA: two dozen working examples on a lightweight harness
Agent builders should review whether this changes evaluation, orchestration, or long-running workflow assumptions.
A 3x3 grid of images showcasing behind-the-scenes film production, soccer training, and video editing software interfaces.
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from blog.google.
YouTube announces new insights tools to support creator partnerships and strengthen ad campaigns at Cannes Lions 2026.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Mistral OCR 4 delivers enterprise document AI with 170-language support, bounding boxes, and self-hosted deployment.
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from mistral.ai.
The GitHub Copilot app now supports bring your own key (BYOK), so you can run agent sessions against your own model providers, including OpenAI, Azure OpenAI, Microsoft Foundry, Anthropic, LM...
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
Blue shield with a lock on it, all in front of various computer windows
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Changes since langchain-openrouter==0.2.3 release(openrouter): 0.2.4 ( #38381 ) chore(openrouter): bump openrouter floor to 0.9.2, drop file workaround ( #38216 ) test(openrouter): cover cache_control passthrough on tool defs ( #38215 ) feat(openrouter): surface parallel_tool_calls on bind_tools ( #38214 ) chore(model
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Discover how Omio uses OpenAI to power conversational travel experiences, accelerate product development, and transform into an AI-native company.
API or pricing changes from openai.com can materially affect production costs and integration plans.
Shipping huggingface_hub every week with AI, open tools, and a human in the loop
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Experimenting with the proposed Cross-Origin Storage API in Transformers.js
API or pricing changes from huggingface.co can materially affect production costs and integration plans.
Changes since langchain-anthropic==1.4.6 hotfix(anthropic): regenerate cassette ( #38376 ) release(anthropic): 1.4.7 ( #38373 ) chore: bump vcrpy from 8.1.1 to 8.2.1 in /libs/partners/anthropic ( #38324 ) chore: bump langsmith from 0.8.5 to 0.8.18 in /libs/partners/anthropic ( #38325 ) docs(anthropic): clarify prompt c
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
Changes since langchain-openai==1.3.2 release(openai): 1.3.3 ( #38375 ) fix(openai): drop response item ids when store is false ( #38372 ) fix(langchain,openai): only set strict=True on tools for OpenAI-compatible models in ProviderStrategy ( #38370 ) test(openai): clarify expected strict schema error ( #38338 ) fix(op
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
What's changed Added claude mcp login and claude mcp logout to authenticate MCP servers from the CLI without opening the interactive /mcp menu, with --no-browser stdin redirect support for completing over SSH Added status filtering (press f ) to the /workflows agent detail view Added a "Skills" section to the /plugin I
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
An aerial view shows the formal gardens and geometric hedgerows of the Governor's Palace in Williamsburg, Virginia, set against a large brick building under a cloudy sky.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Agent builders should review whether this changes evaluation, orchestration, or long-running workflow assumptions.
Google NotebookLM at Florida State University: Transforming Student Success with AI YouTube video
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from blog.google.
This update adds support for organization and enterprise agents from GitHub, lets you queue and steer messages in Copilot CLI sessions, introduces a new agent debug logs summary view, and...
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from github.blog.
Instagram for TV will not be available on Samsung TV, plus we're testing new to make sharing and discovering even more fun.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
OpenAI introduces Patch the Planet, a Daybreak initiative helping open-source maintainers find, validate, and fix vulnerabilities with AI and expert review.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
OpenAI introduces new Daybreak tools, including Codex Security and GPT-5.5-Cyber, to help organizations find, validate, and patch vulnerabilities at scale.
Teams giving assistants data or tool access should review the security failure mode described by openai.com.
This is worth scanning because it may affect how teams choose, deploy, or govern AI tools this week.
Samsung Electronics deploys ChatGPT Enterprise and Codex to employees worldwide, marking one of OpenAI’s largest enterprise AI rollouts.
Enterprise teams should check whether this changes admin control, budget visibility, or deployment governance for tools from openai.com.
What's changed The stream-stall hint now reads "Waiting for API response · will retry in ..." instead of "No response from API · Retrying in ...", and triggers after 20s of silence instead of 10s
Open releases let builders inspect, adapt, or self-host the work instead of relying only on a hosted product.
arXiv:2606.19464v1 Announce Type: new Abstract: Autonomous agentic AI systems driven by Large Language Models (LLMs) introduce a new class of security, privacy, and compliance challenges: an agent that can invoke tools, manipulate data, install software, and coordinate with peer agents across organizational boundaries
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19602v1 Announce Type: new Abstract: Patient contexts span hundreds of heterogeneous documents and thousands of structured data points, yet the document-level metadata that AI systems need for retrieval and triage is absent or incomplete. Standard retrieval-augmented generation fails on this data, mishandlin
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19735v1 Announce Type: new Abstract: While global explanations are crucial for understanding vision models across datasets, classes, and decision contexts, their complex and monolithic nature often hinders practical exploration. Because users typically seek targeted answers to specific questions rather than
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19749v1 Announce Type: new Abstract: A new class of agentic review systems are emerging as a remedy to the pressure placed on peer review systems by AI-assisted research, but it is unclear how they should be evaluated. We evaluate two open-source systems (OpenAIReview and coarse), one proprietary system (Rev
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19771v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced Large Language Model (LLM) reasoning; however, it faces a fundamental optimization instability: uniform token updates precipitate entropy collapse, leading to premature convergence to subopti
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19893v1 Announce Type: new Abstract: Deep research agents have demonstrated remarkable capabilities in autonomous information gathering and synthesis, yet their training remains constrained by the static nature of simulated environments, the limits of fact-retrieval-only task designs, and the inefficiency of
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.20122v1 Announce Type: new Abstract: Open-ended deep research (OEDR) requires systems to acquire knowledge through multi-round retrieval and generate coherent long-form reports. The outline plays a central role as a structural scaffold that coordinates retrieval, evidence organization, and generation.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.20142v1 Announce Type: new Abstract: This paper introduces RACL, a Reasoning-Agent Control Layer for metaheuristics. RACL places a reasoning agent above an existing optimizer.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.20381v1 Announce Type: new Abstract: FP4 training promises substantial reductions in memory and computation cost for LLM pretraining, yet current FP4 hardware paths and recipes, including NVIDIA Blackwell/Rubin-class systems and AMD MI350-series GPUs, remain centered on E2M1 data elements. In this study, we
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19345v1 Announce Type: cross Abstract: The rapid increase in scientific publications leads to the fact that manual study screening in systematic literature reviews (SLRs) is increasingly resource consuming, inefficient, and inconsistent. Classifying studies that clearly report health-related quality-of-life
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19348v1 Announce Type: cross Abstract: We present a preview version of DeepSeek-V4 series, including two strong Mixture-of-Experts (MoE) language models -- DeepSeek-V4-Pro with 1.6T parameters (49B activated) and DeepSeek-V4-Flash with 284B parameters (13B activated) -- both supporting a context length of on
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19361v1 Announce Type: cross Abstract: Identification conditions describe the computability of a target query or parameter of interest as a function of the type and amount of information available. In causal identification, this information is often expressed in the form of a causal graph, and data are obser
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19460v1 Announce Type: cross Abstract: We introduce the first generative foundation model for chest radiograph synthesis trained from scratch at the billion-parameter scale. Existing radiographic AI models often suffer from poor generalisation across patient subpopulations, institutions, and acquisition sett
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19595v1 Announce Type: cross Abstract: Voice agents deployed in structured workflows (customer service, healthcare scheduling, account management) must handle frequent user interruptions while maintaining progress through multi-step procedures. Existing benchmarks for speech-capable models focus on the timin
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19728v1 Announce Type: cross Abstract: Infants are well known to develop their motor skills through dense interaction with caregivers. Although such social interaction is crucial for human development, motor-skill learning in robots is often treated as a unidirectional process in which robots passively recei
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19769v1 Announce Type: cross Abstract: The scalability of humanoid robots will depend not only on models and hardware, but also on whether physical experience can accumulate across robots, tasks, organizations, and time. Drawing on the authors' work in developing ISO/WD 26264-1, Humanoid robot datasets -- Pa
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19795v1 Announce Type: cross Abstract: Electronic design automation (EDA) is inherently multi-stage and handoff-heavy. Design artifacts, flow scripts, and engineering decisions cross tool, session, and organizational boundaries before final implementation, signoff, or release.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19827v1 Announce Type: cross Abstract: Medical tabular data are ubiquitous in clinical research, but deep learning for tables remains underexplored because reliable labels often require costly expert adjudication, even though structured clinical variables are routinely available in tabular form. Self-supervi
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19887v1 Announce Type: cross Abstract: Existing safety benchmarks target general adversarial scenarios but miss finance-specific risks. Financial LLMs face regulatory compliance violations, fraud facilitation, and systemic trust erosion that require targeted evaluation.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.19932v1 Announce Type: cross Abstract: Mamba demonstrates strong efficiency in modeling long visual sequences. However, when token reduction is applied to structurally enhanced Mamba variants, these models exhibit a severe performance collapse.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.20002v1 Announce Type: cross Abstract: This work presents a general framework for training large language models (LLMs) to "Connect the Dots" (CoD), a meta-capability required by long-lifecycle agents: as an LLM-based AI agent gets deployed in an environment, it solves a long sequence of tasks while continuo
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.20041v1 Announce Type: cross Abstract: We propose a model-grounded RAG-based AI economist with an agentic framework for economic scenario analysis using large language models (LLMs) and knowledge graphs. While LLMs can generate fluent economic narratives, economists are often required to make economic claims
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.20388v1 Announce Type: cross Abstract: Data videos integrate dynamic charts, voice narration, and synchronized animations to communicate data insights as temporal narratives, making them an effective medium for improving data consumption efficiency in the data management lifecycle. However, producing high-qu
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2602.07628v2 Announce Type: replace Abstract: While the shift toward unified foundation models has revolutionized many deep learning domains, sleep medicine remains largely restricted to task-specific models that focus on localized micro-structure features. These approaches often neglect the rich, multi-modal con
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2606.15862v2 Announce Type: replace Abstract: Large language model (LLM) agents have made rapid progress on short-horizon, well-scoped tasks, yet their ability to sustain coherent decisions in dynamic long-horizon environments remains uncertain. We introduce RetailBench, a data-grounded simulation benchmark for e
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2503.02636v5 Announce Type: replace-cross Abstract: Resting-state EEG provides a non-invasive view of spontaneous brain activity, but extracting meaningful patterns is often limited by scarce high-quality data and reliance on manually engineered features. Generative adversarial networks (GANs) can synthesize neur
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2507.19712v3 Announce Type: replace-cross Abstract: In this paper, we explore mission assignment and task offloading in an Open Radio Access Network (Open RAN)-based intelligent transportation system (ITS), where autonomous vehicles leverage mobile edge computing for efficient processing. Existing studies often o
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
arXiv:2604.08552v2 Announce Type: replace-cross Abstract: Scientific metadata are often incomplete and noncompliant with community standards, limiting dataset findability, interoperability, and reuse. Even when standard metadata reporting guidelines exist, they typically lack machine-actionable representations.
Researchers and builders should decide whether the result changes evaluation, model design, or agent behavior assumptions.
The Copilot usage metrics API now reports how many AI credits each user consumed per day, derived from the same AI credits consumption data used in the usage-based billing API....
Builders should check whether this changes code review, issue triage, IDE, or repository workflow defaults from github.blog.
We will deprecate Opus 4.6 (fast) across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions), on June 29th, 2026: Model Deprecation date...
An open-source release from github.blog relevant to AI implementation and tooling.
MAI-Code-1-Flash, Microsoft’s purpose-built small coding model, is now available across additional GitHub Copilot surfaces. MAI-Code-1-Flash can now be used in: Copilot CLI GitHub Copilot app Copilot Chat on GitHub Visual...
An open-source release from github.blog relevant to AI implementation and tooling.
Copilot code review now supports repository-level AGENTS.md files, and it’s easier to request a review from Copilot on draft pull requests with the Request button. These changes are all generally...
An open-source release from github.blog relevant to AI implementation and tooling.
Duplicate issues are one of the biggest time sinks for maintainers: triaging the same bug filed multiple ways, closing duplicates, and linking back to the original. For large repositories, this...
An open-source release from github.blog relevant to AI implementation and tooling.
OpenAI introduces new spend controls and usage analytics for ChatGPT Enterprise, helping organizations manage costs and scale AI with confidence.
A model-relevant release from openai.com with potential impact for AI builders.
Searching for pull requests using author: now shows pull requests opened by Copilot cloud agent on the user’s behalf. For example, searching with author:@me on github.com/pulls will return your own...
An open-source release from github.blog relevant to AI implementation and tooling.
You can now quickly jump between repositories without leaving your current page. The new repository switcher in the global navigation is generally available.
An open-source release from github.blog relevant to AI implementation and tooling.
Custom images for GitHub-hosted runners are getting new capabilities that give you more flexibility over how you compose and manage your image-generation pipelines. You can now build custom images on...
An open-source release from github.blog relevant to AI implementation and tooling.
The pull_request_target event is one of the most commonly misused triggers in GitHub Actions, leading to vulnerabilities in workflows. Workflows triggered by pull_request_target run with the base repository’s GITHUB_TOKEN, secrets,...
An open-source release from github.blog relevant to AI implementation and tooling.
Workflow execution protections are now in public preview for GitHub Enterprise, organizations, and repositories. This new capability lets enterprise administrators define an allow list that controls who can trigger GitHub...
An open-source release from github.blog relevant to AI implementation and tooling.
Learn how GPT-5.5 Instant improves ChatGPT’s health and wellness responses with stronger reasoning, better context, clearer communication, and physician-informed evaluations.
A model-relevant release from openai.com with potential impact for AI builders.
When you generate release notes for a new release, the generated notes include a list of pull requests merged since the last release. For more information about automatically generating release...
An open-source release from github.blog relevant to AI implementation and tooling.
Researchers used an OpenAI reasoning model to help diagnose rare diseases, identifying 18 new diagnoses in previously unsolved cases.
A model-relevant release from openai.com with potential impact for AI builders.
arXiv:2606.18543v1 Announce Type: new Abstract: Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service. Yet real-world challenges require a combination of sophisticated skills that remain largely untested in agents: (1) navigating long
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18557v1 Announce Type: new Abstract: A rule-based logic solver resolves every instance in our benchmark in under 50 microseconds with 100% accuracy; the best frontier language model reaches 65% at best and drops to 23.5% under rendering-robust evaluation (worst case over four surface renderings). We introduc
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.19116v1 Announce Type: new Abstract: The World Wide Web was built on an assumption held for three decades: the primary consumer of web content is a human being. This permeates every layer; its access model presumes human visitors, its economics rest on human attention, and its content targets human perceptio
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.19118v1 Announce Type: new Abstract: Electricity markets are inherently complex systems characterised by strong nonlinearities, high-dimensional interactions, and increasing interdependence across regions. While deep neural networks (DNNs) have demonstrated strong predictive capabilities for electricity pric
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects. Existing evaluations often collapse these st
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18485v1 Announce Type: cross Abstract: Neural Text-to-Speech (TTS) systems achieve remarkable quality on short utterances but long-form speech generation shows prosodic drift, speaker inconsistencies and sentence boundary artifacts. Existing approaches either compress sequences, increase context length or na
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18661v1 Announce Type: cross Abstract: Intelligent landslide hazard interpretation is critical for disaster prevention, yet current paradigms struggle to simultaneously extract visual features and high-level geoscientific semantics, while general-purpose vision-language models (VLMs) suffer from perceptual l
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18717v1 Announce Type: cross Abstract: Turkish is agglutinative: meaning is carried by morphemes, yet the subword tokenizers that drive modern language models split words by corpus statistics, fragmenting semantically loaded suffixes and -- in the case of WordPiece and rule-based analyzers -- failing to deco
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18837v1 Announce Type: cross Abstract: Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. However, existing methods face a dilemma between model capability and experience retention.
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18864v1 Announce Type: cross Abstract: This paper studies how to scale learning-based automatic emergency braking (AEB) with massive unlabeled fleet data under production constraints. Our approach is based on meta-feedback semi-supervised learning (MF-SSL), where a teacher generates pseudo labels for unlabel
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.19135v1 Announce Type: cross Abstract: As large language models (LLMs) advance and multi-agent systems aim to overcome the limits of standalone agents, robust communication protocols are becoming essential infrastructure for distributed agent networks. Nonetheless, the fragmented protocol landscape presents
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.19328v1 Announce Type: cross Abstract: Preference-based RL provides an approach to learning reward models from pairwise comparisons of behaviors, bypassing the need for explicit reward design. However, existing methods typically rely on passive data collection and suffer from poor sample efficiency, especial
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2508.21720v3 Announce Type: replace Abstract: Automating scientific poster generation requires hierarchical document understanding and coherent content-layout planning. Existing methods often rely on flat summarization or optimize content and layout separately.
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2512.04144v2 Announce Type: replace Abstract: Targeted interventions on language models, such as unlearning or model editing, aim to modify specific information, but their effects often propagate to related, unintended areas (e.g., removing virology content may degrade performance on allergies); these side-effect
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.11918v2 Announce Type: replace Abstract: Current Large Reasoning Models (LRMs) exhibit remarkable general capabilities but significantly underperform in spatial reasoning tasks. Existing approaches treat this gap as a knowledge deficit, relying on supervised fine-tuning (SFT) to ingest labeled spatial data f
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2303.18031v2 Announce Type: replace-cross Abstract: In real-world applications, a machine learning model is required to handle an open-set recognition (OSR), where unknown classes appear during the inference, in addition to a domain shift, where the data distribution differs between the training and inference pha
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2502.07531v5 Announce Type: replace-cross Abstract: Controllable image-to-video (I2V) generation transforms a reference image into a coherent video guided by user-specified control signals. While precise control over camera motion, object motion, and lighting is essential for high-fidelity creation, existing meth
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2505.16057v2 Announce Type: replace-cross Abstract: AI-Generated (AIG) content has become increasingly widespread by recent advances in generative models and the easy-to-use tools that have significantly lowered the technical barriers for producing highly realistic audio, images, and videos through simple natural
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2506.14126v2 Announce Type: replace-cross Abstract: Modern deep learning is increasingly characterized by the use of open-weight foundation models that can be fine-tuned on specialized datasets. This has led to a proliferation of expert models and adapters, often shared via platforms like HuggingFace and AdapterH
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2510.04120v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance on metaphor detection and interpretation tasks, yet it remains unclear what such behavioral success reveals about metaphor processing. We present a diagnostic analysis that examines the limits of behavioral
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2602.00161v2 Announce Type: replace-cross Abstract: In this paper, we formulate the compression of large language models (LLMs) by optimally deleting transformer blocks (``block removal'') as a constrained binary optimization (CBO) problem that can be mapped to a physical system (Ising glass), whose energies are
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2604.04089v4 Announce Type: replace-cross Abstract: Large language models can write scientific code, but direct paper-to-program translation remains fragile when correctness depends on tacit conventions rather than explicit equations. We frame this as a \textbf{knowledge-externalization} problem: index choices, g
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2604.06367v2 Announce Type: replace-cross Abstract: Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performance~(e.g., WebArena) or safety against malicious actions~(e.g., SafeArena), no existing
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2605.12713v3 Announce Type: replace-cross Abstract: In the field of quantum reservoir computing (QRC), many different computational models and architectures have been proposed. From these models, we identify feedback-based models -- which use a feedback mechanism to re-embed classical measurements from the QRC
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2605.21028v4 Announce Type: replace-cross Abstract: Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks as long-range anchors. However, this fixed allocation keeps early frames cached e
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.02045v2 Announce Type: replace-cross Abstract: Artificial intelligence provides a practical framework for crop damage assessment from imagery data, supporting early decision-making in agricultural management. In peach orchards, climate change increases abiotic stress and biotic pressures, including pests and
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.07150v3 Announce Type: replace-cross Abstract: Agent-interoperability protocols such as A2A and MCP standardize what agents say to one another but assume address-based transport. Whether over HTTP(S) or a content-protecting binding such as MLS-based SLIM, these transports protect message content yet leave th
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.12629v2 Announce Type: replace-cross Abstract: We show the standard basis of transformer hidden states already provides a training-free, architecture-general feature basis. Individual dimensions encode semantic content via their signs (+/-1) and confidence via their magnitudes, acting as independent binary r
A research signal from arxiv.org likely to affect model direction and evaluation choices.
Explore repository content from your terminal without cloning by using two new commands: gh repo read-file and gh repo read-dir. What you can do Use gh repo read-file to read...
An open-source release from github.blog relevant to AI implementation and tooling.
Since our last pattern update, we’ve expanded secret scanning’s detection coverage with new partners, more patterns blocked by push protection by default, additional validity checks, and richer metadata for leaked...
An open-source release from github.blog relevant to AI implementation and tooling.
We’re adding our first governance capability to the enterprise-managed settings configuration. Enterprise administrators can now set disableBypassPermissionsMode to "disable" in the enterprise-managed settings.json to prevent GitHub Copilot CLI and VS...
An open-source release from github.blog relevant to AI implementation and tooling.
GitHub Copilot auto model selection is now generally available in Copilot Chat on github.com and the GitHub mobile app for all Copilot plans. With auto, Copilot chooses a model on...
An open-source release from github.blog relevant to AI implementation and tooling.
Maintainers of open source repositories are dealing with an ever-growing volume of pull requests, including repeated low-quality or drive-by contributions that can slow triage and overwhelm review queues. To help...
An open-source release from github.blog relevant to AI implementation and tooling.
GitHub agent finder is now available. Instead of hand-wiring which MCP servers, skills, canvases, agents, and tools each agent should use-and filling your context window in the process-GitHub Copilot can...
An open-source release from github.blog relevant to AI implementation and tooling.
We’re reopening sign-ups for GitHub Copilot Student, Pro, Pro+, and Max plans gradually over the next couple of weeks for new subscribers. If you’ve been waiting to get started with...
An open-source release from github.blog relevant to AI implementation and tooling.
The GitHub Copilot app is now generally available for macOS, Windows, and Linux. It’s the desktop home for agent-driven development, built natively on GitHub.
An open-source release from github.blog relevant to AI implementation and tooling.
OpenAI and Molecule.one show how a near-autonomous AI chemist using GPT-5.4 improved a key drug-making reaction, advancing medicinal chemistry research.
A model-relevant release from openai.com with potential impact for AI builders.
arXiv:2606.17637v1 Announce Type: new Abstract: Building Management Systems (BMS) are essential for optimizing energy efficiency and operational performance in modern buildings. However, the lack of standardization across BMS points from different manufacturers creates significant barriers to integration and data utili
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17645v1 Announce Type: new Abstract: Large language model (LLM) web agents are usually deployed as tool callers: each turn, the model reads a fresh page observation and emits one structured tool action. When every action is a low-level primitive, horizons grow quickly and so do policy-facing LLM completions
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17696v1 Announce Type: new Abstract: Parametric computer-aided design records both final geometry and the ordered construction history that determines how a part can be edited. Datasets for editable CAD research should therefore expose modeling operations, parameters, and feature dependencies together with v
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17727v1 Announce Type: new Abstract: Recent vision-language models (VLMs) have shown promising progress in generating webpages from visual inputs, yet existing evaluations mainly focus on short, single-screen, and largely static webpages. We introduce LongWebBench, a benchmark for evaluating long-horizon web
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18132v1 Announce Type: new Abstract: Meta-reinforcement learning enables fast adaptation by extracting shared structure from related tasks, but existing end-to-end methods often couple task inference with embodiment-specific control. This coupling can obscure non-parametric task semantics, reduce sample effi
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17059v1 Announce Type: cross Abstract: Prefix caching can reduce LLM inference latency by reusing KV caches across requests with shared prompts, but cluster-scale reuse is challenging because caches are partitioned across nodes. We propose a decentralized, prefix-cache-aware routing scheme for peer-to-peer L
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17077v1 Announce Type: cross Abstract: Proton dissociation constants (pKa) are critical for functional molecule discovery and molecular modeling. Building on iBonD, the largest experimental pKa database established, we and other researchers have developed several methods including machine-learning-based empi
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17081v1 Announce Type: cross Abstract: Disaggregated inference architectures physically separate prefill and decode phases onto distinct GPU pools, creating competing "agents" that share a fixed hardware budget. We provide, to our knowledge, the first formal game-theoretic analysis of this architecture, usin
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17090v1 Announce Type: cross Abstract: ANEForge is a Python package that programs the Apple Neural Engine (ANE), the fixed-function neural accelerator on every recent Apple device, directly and without CoreML. In production the engine is reachable only through CoreML, which treats it as a scheduling option:
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17379v1 Announce Type: cross Abstract: Accurate intraoperative liver registration is challenging due to substantial soft-tissue deformation yet sparse intraoperative measurements. Biomechanical models regularize this ill-posedness with prior knowledge but exhibit persistent prediction bias due to simplifying
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17646v1 Announce Type: cross Abstract: Saliency map visualizations explain image-based AI predictions by pointing to regions, but these are often unintuitive and semantically unclear, leaving an interpretability gap. We argue that AI explanations should be intuitive -- coherent to user knowledge, yet simple
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17660v1 Announce Type: cross Abstract: Fine-tuning large language models (LLMs) is compute-intensive and error-prone: model performance depends sensitively on data quality and hyperparameter choices, and na\"ive runs can even degrade model performance. This raises a practical question:can we predict fine-tun
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17702v1 Announce Type: cross Abstract: Characterising the tumour microenvironment (TME) from routine H&E-stained histology images requires simultaneous cell segmentation, feature extraction, and interpretable clinical reporting. We present SEGTME-UNI2, a unified framework addressing these requirements.
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17924v1 Announce Type: cross Abstract: Current Vision-Language-Action (VLA) models face a trade-off between efficient action generation and explicit deliberation. Directly decoding actions from vision-language backbone representations enables low-latency control, whereas explicit reasoning through textual ch
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.17989v1 Announce Type: cross Abstract: Multi-contrast magnetic resonance imaging (MRI) provides complementary information for clinical diagnosis. However, acquiring all MRI sequences is often time-consuming and costly.
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18120v1 Announce Type: cross Abstract: Large language model applications build prompts from templates, and Handlebars is a widely used templating engine and the default prompt-template format in Microsoft Semantic Kernel. Its double-brace {{x}} expression HTML-escapes the interpolated value and is documented
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18135v1 Announce Type: cross Abstract: In this work, we introduce the Certus Caliber Classification Gunshot Dataset (C3GD), a publicly accessible data set developed for the analysis of firearm muzzle blast sounds. The dataset aims to provide a wide variety of firearms, calibers, cartridges, microphones, and
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18156v1 Announce Type: cross Abstract: We present a novel framework for realistic and controllable 3D face re-aging which produces highly detailed, identity-preserving results. Existing 3D editing methods, while effective for coarse semantic changes, are not well suited for re-aging, as even small inconsiste
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18168v1 Announce Type: cross Abstract: Software practitioners increasingly use AI coding agents that generate test code alongside production code in open source pull requests (PRs). Recent studies report more than 932,000 agent-authored PRs across more than 116,000 repositories, yet whether their test files
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18193v1 Announce Type: cross Abstract: We evaluate the adversarial robustness of two frontier large language models (LLMs) developed by Anthropic, Fable 5 and Opus 4.8, against four families of automated jailbreak attack across 7 826 harmful intents spanning a ten-category harm taxonomy. Using the HackAgent
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2606.18203v1 Announce Type: cross Abstract: The LLM-empowered personal health agents with user health (sensor) metrics have offered a promising pathway to alleviate global disparities in healthcare access. However, large-scale clinical deployment remains constrained by an open-ended evaluation bottleneck: physici
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2605.30036v2 Announce Type: replace Abstract: Large Language Models (LLMs) demonstrate a remarkable capacity to adopt different personas and roles; however, it remains unclear whether they can manifest behavior that adheres to a coherent, human-like value structure. In this work, we draw on established psychologi
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2510.01359v2 Announce Type: replace-cross Abstract: Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, raising "jailbreak" stakes beyond text-only settings. Prior evaluations emphasize refusal or harmful-text detection, leavi
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2510.21583v3 Announce Type: replace-cross Abstract: Recent Progress in post-training flow matching for text-to-image (T2I) generation with Group Relative Policy Optimization (GRPO) has demonstrated strong potential. However, it is hindered by a critical limitation: inaccurate advantage attribution.
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2601.16407v4 Announce Type: replace-cross Abstract: Large language models (LLMs) make next-token predictions based on clues present in their context, such as semantic descriptions and in-context examples. Yet, elucidating which prior tokens most strongly influence a given prediction remains challenging due to the
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2603.03485v3 Announce Type: replace-cross Abstract: Recent video diffusion models have achieved impressive capabilities as large-scale generative world models. However, these models often struggle with fine-grained physical consistency, exhibiting physically implausible dynamics over time.
A research signal from arxiv.org likely to affect model direction and evaluation choices.
arXiv:2605.29179v2 Announce Type: replace-cross Abstract: Metal-organic frameworks (MOFs) are excellent candidates for water harvesting due to their tunable pore environments, which can be precisely engineered to capture and release water in arid conditions. Integrating artificial intelligence (AI) into MOF discovery c
A research signal from arxiv.org likely to affect model direction and evaluation choices.
Introducing LifeSciBench, an expert-authored, expert-reviewed benchmark for evaluating how AI systems handle real-world life science research tasks and decisions.
A research signal from openai.com likely to affect model direction and evaluation choices.
Varonis Threat Labs disclosed a 3-stage chain (parameter-to-prompt injection, HTML-injection race, and SSRF via Bing) in M365 Copilot Enterprise Search that turns Copilot into a one-click data exfiltration tool against any user who clicks an attacker-crafted link. Microsoft assigned CVE-2026-26137 and began rolling out
SearchLeak is a working, one-click enterprise data exfiltration chain against the most-deployed AI assistant in the Microsoft 365 stack, and the same parameter-to-prompt pattern recurs across many enterprise RAG systems.
GitHub now runs CodeQL, GitHub Advisory Database dependency checks, and secret scanning on code produced by third-party coding agents (Claude, OpenAI Codex) before the PR finalizes. The validation is on by default, with no action required from repo owners.
Default-on security scanning for AI-generated PRs changes the security baseline of every GitHub repo that enables coding agents, and the same model is now an industry template other code hosts are likely to copy.
The US Commerce Department ordered Anthropic on June 12 to cut off Fable 5 and Mythos 5 for all foreign nationals; Anthropic disabled both models globally rather than try to segment users. In-person talks between Anthropic leadership and White House officials are ongoing.
Anthropic's global takedown of two flagship models sets a major precedent for how US AI vendors respond to export-control orders and exposes the practical limits of national-segmentation strategies for frontier models.
Effective June 15, Pro/Max/Team/Enterprise plans get a fixed monthly 'Agent SDK credit' pool ($20 Pro, $100 Max 5x, $200 Max 20x, $20 Team Standard, $100 Team Premium). When exhausted, SDK and headless 'claude -p' calls no longer silently count toward the standard message limit and instead degrade or require an upgrade
Anthropic is moving agent and headless usage onto a separate, predictable billing lane, which is a significant change for anyone running autonomous agents or CI on Claude and forces a re-read of every cost projection.
OpenAI released GPT-5, describing a unified system that routes between a fast default model and a deeper reasoning model, with a 256k context window, vision input, and improvements on coding, math, and multimodal benchmarks.
GPT-5 is the default model behind ChatGPT and the OpenAI API, so this release changes what hundreds of AI products and coding tools can do for hundreds of millions of users.
Anthropic released Claude Opus 4.1, an upgrade to Claude Opus 4 focused on agentic tasks, real-world coding, and reasoning, with a 200k context window and improved tool use.
Opus 4.1 is the strongest Anthropic coding model and is the default in Claude Code for many enterprise coding workflows, so a release here directly affects AI-assisted software quality.
Google DeepMind released Gemini 2.5 Pro Deep Think, a reasoning mode that uses parallel thinking to tackle hard math, coding, and multimodal problems, available to Google AI Ultra subscribers.
Deep Think is the first widely available consumer-facing parallel-reasoning model, and it sets a new bar on hard reasoning benchmarks; pricing and access shape how teams adopt it.
Hugging Face released SmolLM3, a 3B-parameter open-weight model with both thinking and non-thinking modes, an Apache-2.0 license, and full training-data recipe; it competes with much larger proprietary models on reasoning benchmarks.
A 3B model that rivals larger closed models in reasoning and ships fully open changes what local AI can do on a laptop, and it gives builders a real base for fine-tuning without GPU cluster costs.
Mistral released Magistral, a reasoning model family in Small (24B, Apache-2.0) and Medium (enterprise) variants, optimized for chain-of-thought across math, coding, and multi-step agent tasks.
Mistral's first openly licensed reasoning model is a clear signal that the open-weight model race is now competing with closed labs on chain-of-thought quality, not just base chat quality.
GitHub launched a Copilot coding agent that can pick up GitHub issues, open a pull request, and iterate on CI feedback, with humans able to review and request changes at every step.
The Copilot coding agent brings autonomous repo work into the world's largest code-hosting platform, setting a new baseline for what 'agentic' means in mainstream developer tooling.
Meta released Llama 4 Scout (17B active, 10M context) and Llama 4 Maverick (17B active, 400B total) as open-weight, mixture-of-experts models with native multimodality across text, image, and video.
Open-weight models with 10M-token context and native multimodal training are new territory for the open ecosystem; they make long-context document and video tasks feasible without API costs.
DeepSeek released R1, an MIT-licensed open-weight reasoning model with publicly documented training pipeline and strong benchmark results on math, coding, and scientific reasoning, alongside the smaller R1-Distill family.
DeepSeek-R1 is the first open-weight reasoning model to match closed frontier models on key benchmarks at a fraction of the cost, and it changed how enterprises and governments think about open AI stacks.
OpenAI introduced Sora, a text-to-video model that can generate up to 60-second clips with multi-shot scenes, persistent characters, and physics-aware motion, and rolled it out to ChatGPT and the OpenAI API in stages.
Sora is the first widely available consumer-facing text-to-video model at this fidelity, and it kicked off a wave of competing video-generation launches from Google, Meta, Runway, and others.
Anthropic released the Model Context Protocol (MCP), an open standard that lets AI assistants connect to data sources and tools through a single interface, and donated it to a new open-governance foundation.
MCP is becoming the de facto standard for connecting agents to tools and data; supporting it has become table stakes for any serious coding agent, IDE, or enterprise AI platform.
Anthropic released a beta of Computer Use, a Claude capability that lets the model see and operate a real desktop by taking screenshots, moving the cursor, and clicking, with safety guidance for high-impact actions.
Computer Use turned Claude into a general-purpose browser-and-desktop agent and kicked off the wave of GUI agents that now ship in browsers, IDEs, and enterprise automation products.
OpenAI released the Realtime API, with speech-to-speech models that handle interruptions, function calling, and tone detection, enabling production voice agents in a single API call.
Production voice agents previously required stitching together STT, LLM, and TTS; the Realtime API made it possible to ship conversational voice products in days rather than months.
OpenAI released Structured Outputs, which guarantees model responses match a developer-supplied JSON schema, and made the feature available across GPT-4o and its smaller models at no extra cost.
Reliable JSON-schema compliance is the foundation for production agent systems, tool calls, and database writes, and Structured Outputs removes the biggest source of brittleness in production LLM code.
Anthropic released Claude 3.5 Sonnet, with state-of-the-art results on coding, reasoning, and vision benchmarks at one-fifth the cost of Claude 3 Opus, plus a 200k context window and an upgraded Artifacts workspace.
Claude 3.5 Sonnet set a new cost-to-capability ratio for frontier models and became the default for many coding-agent products, so its release reshaped pricing across the API market.