AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- LessWrongcommunityThe Convex Hull Armada
Epistemic status: I am not a subject-matter expert in any of the fields in this article. The following is speculation, albeit I think reasonable speculation. Cunningham’s Law is why I wrote this essay. AI Disclosure: Cla…
- arXiv cs.AIresearchAn Explainable Header-Centric Framework for Large-Scale Semantic Table Interpretation and Data Quality Assessment
arXiv:2610.10541v1 Announce Type: new Abstract: Knowledge Graph (KG) quality depends not only on downstream graph validation, but also on the quality of tabular metadata used before integration. In metadata-only Semantic…
- arXiv cs.AIagentsSynthesis Through Simulation: Generating Coherent Enterprise Data via Scalable Agent-System Interaction
arXiv:2610.10549v2 Announce Type: replace Abstract: Tool-calling agents have become central to enterprise AI, yet training and evaluating them at scale remains severely constrained due to business and legal restrictions…
- arXiv cs.AIagentsAgent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice
arXiv:2610.10590v1 Announce Type: new Abstract: Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload. We study agent-controlled forgetting: the acting model…
- arXiv cs.AIagentsVerification and Self-Improvement in Agentic AI: Foundations and Limits
arXiv:2610.10611v2 Announce Type: replace Abstract: A self-improving agent can find accepted solutions more often without expanding the tasks its verification interface can accept. We extend task-relative verification wi…
- arXiv cs.AIagentsThe Harness as the Only Mutable Surface: Compliance-Bounded Self-Evolution of LLM Agents in Credit Pipelines, with a Measured Admission Gate
arXiv:2610.10629v1 Announce Type: new Abstract: Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a named change, a rec…
- arXiv cs.AIagentsSpeaking the Navigator's Language: Trajectory-Grounded Instruction Translation for Frozen Aerial VLN Agents
arXiv:2610.10635v1 Announce Type: new Abstract: Aerial vision-and-language navigation (VLN) agents are typically trained on detail-rich, trajectory-aligned commands, whereas users issue short, intent-driven instructions;…
- arXiv cs.AIagentsPlan-and-Patch: Diffusion Language Models for Agentic Planning
arXiv:2610.10786v1 Announce Type: new Abstract: Planning is increasingly important for long-horizon agents, where successful execution requires coordinating subgoals, tool use, and intermediate outcomes over many steps.…
- arXiv cs.AIresearchWhose Ground Truth? Embracing Ambiguity in Human-Centered AI
arXiv:2610.10805v1 Announce Type: new Abstract: As AI systems increasingly interact with people and make decisions about them, understanding human interpretations becomes an important part of developing human-centered AI…
- arXiv cs.AIagentsOn the Clock: Towards Punctual and Productive Time-Budgeted AI Agents
arXiv:2610.10833v1 Announce Type: new Abstract: We study whether small LLM agents can operate effectively under explicit wall-clock time budgets by both respecting the allocated runtime and using available time productiv…
- arXiv cs.AIresearchSelf-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning
arXiv:2610.10857v1 Announce Type: new Abstract: Behavior cloning (BC) in non-Markovian environments is a challenging problem because policies have to reason over contextual information over long horizons. Existing policy…
- arXiv cs.AIagentsReading the Room: Foundations, Design, and Challenges of Normative Competence in LLMs
arXiv:2610.10906v2 Announce Type: replace Abstract: Human communities are governed by normative systems: shared standards that produce \textit{norms} dictating acceptable behavior, enforced through community sanctioning.…
- arXiv cs.AIagentsStoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents
arXiv:2610.10942v1 Announce Type: new Abstract: Reinforcement learning environments are now a primary lever for improving large language model (LLM) capabilities in post-training, yet most agentic benchmarks remain stati…
- arXiv cs.AIresearchLearning How to Search for Plans with Exponentially Less Space
arXiv:2610.10954v1 Announce Type: new Abstract: Heuristic search for a plan can store exponentially many states, even when its heuristic is almost perfect. We instead learn search control, one specification per domain, w…
- arXiv cs.AIresearchHow Narrative Wrapping Affects LLM Refusal: A Cross-Language Benchmark and Defense
arXiv:2610.11005v2 Announce Type: replace Abstract: Safety-aligned language models often refuse a harmful request stated directly but answer the same request inside a role-play or narrative wrapper. We measure this vulne…
- arXiv cs.AIagentsCurating Always-Loaded Context for LLM Agents: A Capacitated Assortment Model with Censored Feedback
arXiv:2610.11007v1 Announce Type: new Abstract: At the start of every session, LLM agents load a fixed context file, such as $\texttt{AGENTS.md}$. Each loaded token in the file is charged again in every later round of th…
- arXiv cs.AIresearchDistillation for Incrimination and Distillation for Capabilities
arXiv:2610.11012v1 Announce Type: new Abstract: Powerful misaligned AI models might recognize alignment evaluations and strategically behave well on them, rendering direct audits uninformative. However, distilling such a…
- arXiv cs.AIagentsAgentHorizon: Evaluating Agentic Judges for Long-Horizon Computer-Use Tasks
arXiv:2610.11050v1 Announce Type: new Abstract: Computer-use agents are capable of completing complex tasks, increasing the use of automatic judges to determine success, either for training or for evaluation without huma…
- arXiv cs.AIresearchBeyond Imitation: A Framework and Benchmark for LLM-Assisted Peer Review
arXiv:2610.11087v1 Announce Type: new Abstract: The rapid growth of scientific publishing has strained peer review, particularly in machine learning, raising concerns about declining review quality and increasing reviewe…
- arXiv cs.AIresearchOpenProblemBench: Benchmarking AI on Open Problems in the Foundational Theoretical Sciences
arXiv:2610.11118v1 Announce Type: new Abstract: The next frontier for artificial general intelligence is tackling unresolved scientific problems, calling for benchmarks that assess progress beyond established knowledge.…
- arXiv cs.AIagentsWhen Interfaces Speak: Data-Aware Generative UI Harness for Active Interaction
arXiv:2610.11123v1 Announce Type: new Abstract: Most human-agent interaction today remains text-based. Natural language can impose cognitive overload, ambiguity, information chaos, and slow input for complex tasks; ephem…
- arXiv cs.AIresearchBalancing Reference Guidance and Free Generation in Trajectory Rollouts for Reasoning RL
arXiv:2610.11128v1 Announce Type: new Abstract: A verified reference solution provides a correct trajectory for training a reasoning model. Alternatively, a prefix of the reference can guide the model in generating a tra…
- arXiv cs.AIresearchGameCommBench: A Unified Benchmark and Type-Aware Evaluation for AI-Generated Game Commentary
arXiv:2610.11129v1 Announce Type: new Abstract: Game commentary is an open-ended generation task requiring multimodal perception, strategic reasoning, and contextual knowledge. Existing AI-Generated Game Commentary (AI-G…
- arXiv cs.AIresearchSocial Pain Disrupts Emotion-Action Brain-State Dynamics in Adolescents with Non-Suicidal Self-Injury
arXiv:2610.11155v1 Announce Type: new Abstract: Non-suicidal self-injury (NSSI) is prevalent among adolescents with depression, but the rapid brain-state dynamics linking social distress to maladaptive behavior remain un…
- arXiv cs.AIagentsWhat to Admit and How to Present: Governing Persistent Memory in LLM Agents
arXiv:2610.11188v1 Announce Type: new Abstract: Persistent memory can improve personalization in LLM agents but can also induce sycophancy and cross-domain leakage. We distinguish two governance decisions: admission, whi…
- arXiv cs.AIresearchAliO: Output Alignment Matters in Long-Term Time Series Forecasing
arXiv:2610.11213v2 Announce Type: replace Abstract: Long-term Time Series Forecasting (LTSF) tasks, which leverage the current data sequence as input to predict the future sequence, have become increasingly crucial in re…
- arXiv cs.AIresearchWhen Lower Reconstruction Loss Hurts: Distributionally Robust Refinement for Low-Bit LLM Quantization
arXiv:2610.11226v1 Announce Type: new Abstract: Weight-only post-training quantization (PTQ) relies heavily on reconstruction loss minimization to preserve model quality at low precision. We show that the weights favored…
- arXiv cs.AIresearchHarness Compilation: Which Decisions Should a Small Vision-Language Model Keep?
arXiv:2610.11231v1 Announce Type: new Abstract: Small vision-language models may be able to read external evidence yet struggle to obtain it. We introduce Harness Compilation (HC), an offline procedure that adapts the di…
- arXiv cs.AIagentsLLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models
arXiv:2610.11253v1 Announce Type: new Abstract: Large language model agents are being increasingly deployed as autonomous scientists, designing experiments and inferring mechanistic world models with minimal human oversi…
- arXiv cs.AIagentsTaReD: Tool-Aware Recursive Decomposition for Long-Horizon Tasks
arXiv:2610.11268v1 Announce Type: new Abstract: Agents combine reasoning with tools to interact with external systems and complete real-world tasks. Early agents typically interleave reasoning and actions along a single…
- arXiv cs.AIagentsOpen-ended Scientific Discovery with Possibilistic Reasoning
arXiv:2610.11289v1 Announce Type: new Abstract: Autonomous scientific discovery with LLMs requires generating and testing hypotheses adaptively as evidence accumulates while maintaining statistical validity. Existing any…
- arXiv cs.AIresearchORDO: Operation-level Round-aware Dynamic Ordering for MIP Presolve
arXiv:2610.11294v1 Announce Type: new Abstract: Presolve strongly affects mixed-integer programming (MIP) performance, yet learning-based methods only optimize parameter configurations and cannot express the non-commutat…
- arXiv cs.AIagentsDuplexAgent-RSI: Recursive Harness Improvement for Full-Duplex Voice Agent Collaboration
arXiv:2610.11299v1 Announce Type: new Abstract: Voice agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live channel as the entry to the conversation, while search, reasoning,…
- arXiv cs.AIagentsMedBenchAgent: Towards Systematic Automation of Medical VLM Benchmark Construction
arXiv:2610.11312v1 Announce Type: new Abstract: Large-scale construction of medical vision-language model (VLM) benchmarks is increasingly feasible with richly annotated imaging datasets and large language models (LLMs),…
- arXiv cs.AIresearchDivMoE: Fine-Grained MoE Upcycling via Cross-Domain Expert Composition
arXiv:2610.11317v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures have become essential for scaling large language models, with recent work demonstrating the benefits of fine-grained expert designs.…
- arXiv cs.AIresearchFinsler Flow Matching: Dynamics-Aware Geodesic Interpolation for Single-Snapshot Trajectory Inference
arXiv:2610.11318v1 Announce Type: new Abstract: Single-cell snapshot data can resolve a continuum of cellular states but do not uniquely determine the dynamics governing transitions between them. However, additional dyna…
- arXiv cs.AIagentsMine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wild
arXiv:2610.11328v1 Announce Type: new Abstract: Advances in foundation models are driving efforts to introduce agents to assist people in the physical world. Such agents require agentic spatial intelligence: exploring un…
- arXiv cs.AIresearchTokenBank: Financial Infrastructure for AI Services
arXiv:2610.11333v1 Announce Type: new Abstract: AI services incur inference costs during execution, while revenue may arrive later. Changing API prices, limited upfront capital, and service failures can limit operators'…
- arXiv cs.AIagentsReCast: Attribution-Oriented Step Representation Learning for LLM-Based Agent Systems
arXiv:2610.11334v1 Announce Type: new Abstract: In LLM-based agent systems, failures can originate from early steps whose effects propagate through subsequent interactions, making their origins difficult to identify. To…
- arXiv cs.AIresearchEvoSim: Learning to Model, Modeling to Learn
arXiv:2610.11344v1 Announce Type: new Abstract: Physics-based models connect scientific explanation with quantitative prediction. Constructing them requires selecting physical processes, defining states and governing equ…
- arXiv cs.AIagentsSynCo: Data Synthesis Co-Training for Self-Evolving LLMs via Multi-Agent Reinforcement Learning
arXiv:2610.11345v1 Announce Type: new Abstract: Self-evolving LLM agents promise to improve autonomously through continual interaction and learning, reducing their dependence on manually curated supervision. Realizing th…
- arXiv cs.AIresearchRL-ARC: Calibrating Large Reasoning Models via Reasoning-guided Uncertainty
arXiv:2610.11352v1 Announce Type: new Abstract: Language models (LMs) are commonly trained with Reinforcement Learning with Verifiable Rewards (RLVR) to enhance their reasoning capabilities. However, since RLVR does not…
- arXiv cs.AIresearchDefensive Writing in GPT Models
arXiv:2610.11355v2 Announce Type: replace Abstract: Researchers increasingly use ChatGPT to revise their papers, and when asked to make a paper hold up under review, recent GPT versions often narrow or even retract the a…
- arXiv cs.AIagentsRaReCache: Bridging the Gap in Cross-Model KV Cache Reuse via Rank disagreement-based Selective Recomputation
arXiv:2610.11358v1 Announce Type: new Abstract: Cross-model KV-cache reuse remains a key challenge in modern LLM serving. Coding agents and multi-model systems increasingly route a shared context across models: a user ma…
- arXiv cs.AIresearchUniData: Universal Multimodal Instruction Generation Pipeline
arXiv:2610.11363v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are increasingly being applied in a wider range of real-world scenarios. However, due to the substantial labor cost, creating high-…
- arXiv cs.AIagentsRIT-RAG: Navigating Document Corpora with Retrieval-Induced Trees
arXiv:2610.11370v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) grounds language models in external corpora. Agentic RAG enables iterative search, yet exposes the model to isolated chunks without…
- arXiv cs.AIresearchEqual Path Cost, Unequal Output Effects: Understanding Perturbation Propagation in Diffusion Models
arXiv:2610.11380v1 Announce Type: new Abstract: Diffusion models have achieved remarkable success in generative modeling, with their sampling procedures routinely modified to control generation and improve efficiency. Th…
- arXiv cs.AIagentsEnvironmental Feedback Modeling Matters: Rethinking Feedback Treatment in Agentic Hindsight Self-Distillation
arXiv:2610.11384v1 Announce Type: new Abstract: Reinforcement learning is commonly used to train language agents in interactive environments, but cannot be directly applied when rewards are unavailable. Recent methods us…
- arXiv cs.AIresearchTypedBench: A Benchmark for Calibration, Framing Sensitivity, and Cost in System One Decision Models
arXiv:2610.11392v2 Announce Type: replace Abstract: System One models output calibrated probabilities over typed answers such as categorical choices, ordinal levels, or binary outcomes, via a non-generative interface. So…
- arXiv cs.AIresearchEstimating Great Expectations Under Autoregressive Language Models with Potentials
arXiv:2610.11399v3 Announce Type: replace Abstract: Many applications of language models require estimating the expectation of a test functional under the model. Obtaining precise estimates can be computationally expensi…