AI news archive.
19,861 articles, newest first, from the outlets listed on the sources page.
- arXiv cs.AIresearchA Node Embedding Framework for Model-Centric Conformance Checking in Process Mining
arXiv:2610.17702v1 Announce Type: new Abstract: Evaluating the quality of process models discovered from event logs is a fundamental challenge in process mining. Traditional evaluation relies on conformance metrics such…
- arXiv cs.AIagentsAdaptive-Group Process Rewards for GUI Agents
arXiv:2610.17710v2 Announce Type: replace Abstract: Training graphical user interface (GUI) agents with reinforcement learning suffers from sparse outcome rewards, leading to inefficient learning. Process rewards offer a…
- arXiv cs.AIresearchECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution
arXiv:2610.17718v2 Announce Type: replace Abstract: Electrocardiogram (ECG) models need supervision that targets evolving weaknesses and remains faithful to waveform evidence. We introduce ECG-RSI, a recursive self-impro…
- arXiv cs.AIagentsKeep Your Receipts: Trustworthy Cleanup of Agent-Built Knowledge Graphs
arXiv:2610.17719v1 Announce Type: new Abstract: Agents build knowledge graphs as memory, and building them has become easy. Maintaining them has not. When a source is retracted, overruled, or erased, everything built on…
- arXiv cs.AIagentsUpstream Influence, Downstream Re-Anchoring in LLM Agent Chains
arXiv:2610.17723v1 Announce Type: new Abstract: People act on evaluative judgments produced by LLM agents, and in multi-agent systems those judgments pass through several agents before reaching a person. We show that a w…
- arXiv cs.AIagentsEvidence-First Agentic Verification
arXiv:2610.17724v1 Announce Type: new Abstract: Long-horizon, semi-verifiable agentic tasks often rely on rubric-based evaluation, but the evidence needed to assess these tasks can be spread across the environment state…
- arXiv cs.AIagentsSafety for Whom? Benchmarking Understanding Beyond Refusal in Egocentric Multimodal Assistants
arXiv:2610.17728v1 Announce Type: new Abstract: Egocentric multimodal assistants see through the user's eyes and guide what the user does next, so their outputs directly shape physical actions, including those that affec…
- arXiv cs.AIresearchDuplexAct: How Interactive Are Frontier Full-Duplex Spoken Language Models?
arXiv:2610.17738v1 Announce Type: new Abstract: End-to-end (E2E) full-duplex spoken language models (FD-SLMs) enable simutanous listening and speaking continously, requiring models to take appropriate interaction actions…
- arXiv cs.AIresearchCoupled Harness--Model Evolution for Scientific Equation Discovery
arXiv:2610.17740v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that must work together: a…
- arXiv cs.AIagentsInstructions Are Evidence, Not Objectives: Measuring Outcome Alignment of Agents
arXiv:2610.17757v1 Announce Type: new Abstract: Large language model agents can follow complex human instructions to solve real-world tasks. In practice, however, initial instructions are often incomplete. In our analysi…
- arXiv cs.AIagentsAutonomous 3D Visual-Thermal Inspection for Utility-Scale Solar Farms
arXiv:2610.17762v1 Announce Type: new Abstract: Utility-scale photovoltaic (PV) inspection is dominated by aerial surveys, which are effective for identifying module-level hot cells but provide limited visibility of crit…
- arXiv cs.AIagentsMemory Echo in Single-Agent Long-Term Memory: Lifecycle Evaluation and Provenance-Guided Mitigation
arXiv:2610.17763v1 Announce Type: new Abstract: Long-term memory supports agents across sessions. Repeated retrieval and write-back can let one historical claim occupy multiple retrieval positions and influence current a…
- arXiv cs.AIagentsAgentic4PDM: Host-Governed Evidence Admissibility for Industrial Fault Diagnosis
arXiv:2610.17786v1 Announce Type: new Abstract: We study industrial fault diagnosis as a classification task that assigns sensor time-series windows to predefined health states or fault types. Scarce labels and changing…
- arXiv cs.AIagentsEmpowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution
arXiv:2610.17816v2 Announce Type: replace Abstract: Edge-cloud collaboration combines the lower inference overhead and greater data locality of edge-side execution with the stronger capabilities of cloud-hosted models. H…
- arXiv cs.AIagentsBenchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents
arXiv:2610.17827v1 Announce Type: new Abstract: Existing approaches to training and evaluating search agents focus heavily on final-answer quality, largely neglecting how generated answers map back to retrieved evidence.…
- arXiv cs.AIagentsLearning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Models
arXiv:2610.17840v1 Announce Type: new Abstract: Multi-agent deliberation can improve recognition by criticizing and revising candidate answers, but fixed controls cannot respond to changes in disagreement or reasoning qu…
- arXiv cs.AIagentsSocratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills
arXiv:2610.17860v1 Announce Type: new Abstract: Agent Skills improve LLM agents by making task knowledge reusable across sessions. Learning transferable Skills requires evidence about a procedure and its conditions of us…
- arXiv cs.AIagentsECMR: Evidence-Aware Deliberation Control for Multi-Agent LLM Reasoning
arXiv:2610.17869v1 Announce Type: new Abstract: Multi-agent Large Language Model (LLM) systems typically commit to a deliberation protocol before inference. A fixed protocol cannot allocate computation differently to res…
- arXiv cs.AIagentsTraining LLMs for Multi-Agent Collaboration with Verifiable Information Rewards
arXiv:2610.17893v1 Announce Type: new Abstract: Effective collaboration among large language model (LLM) agents in multi-agent systems requires sharing relevant evidence, requesting missing information, and incorporating…
- arXiv cs.AIresearchPaceReasoner: Label-Free Learning to Answer Briefly from Long Reasoning
arXiv:2610.17900v1 Announce Type: new Abstract: Extended chain-of-thought reasoning improves problem-solving performance but increases inference cost and latency, motivating more accurate answers with shorter reasoning.…
- arXiv cs.AIagentsLearning How to Remember: Memory Modality Selection for GUI Agents
arXiv:2610.17928v1 Announce Type: new Abstract: Recent advances in vision-language models (VLMs) have substantially improved the capabilities of GUI agents, while memory augmentation has emerged as a promising approach f…
- arXiv cs.AIresearchSeeing Depth but Choosing Cues in Vision-Language Models
arXiv:2610.17976v1 Announce Type: new Abstract: Do vision-language models use depth information to judge which object is closer, or rely on image-plane cues? We investigate this question through controlled depth--cue con…
- arXiv cs.AIresearchSHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces
arXiv:2610.18025v1 Announce Type: new Abstract: Test-time scaling has enabled LLMs to solve increasingly complex reasoning, discovery, and optimization tasks. However, existing approaches often gather observations while…
- arXiv cs.AIresearchBeyond Black Boxes: Visual Grounding for Text Embeddings
arXiv:2610.18047v1 Announce Type: new Abstract: In this paper, our goal is to represent text embeddings as sketches for three main reasons. First, to visualize text representation and to explore their potential their pot…
- arXiv cs.AIagentsCan Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents
arXiv:2610.18052v1 Announce Type: new Abstract: Long-term memory has become a core component of large language model (LLM) agents. As agents accumulate personal information over long-term use, users increasingly ask them…
- arXiv cs.AIagentsWorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution
arXiv:2610.18067v1 Announce Type: new Abstract: Scaling interactive environments is important for training long-horizon agents through reinforcement learning. These environments often require further testing and refineme…
- arXiv cs.AIagentsAReaL-RSI: Adaptive Scaling and Coordination of Recursive Self-Improvement
arXiv:2610.18083v1 Announce Type: new Abstract: Scaling recursive self-improvement requires additional computation to produce useful research progress in reaching persistent objectives. Intuitively, more researcher agent…
- arXiv cs.AIagentsResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch
arXiv:2610.18088v2 Announce Type: replace Abstract: Autoresearch systems increasingly undertake entire research projects. In practice, scientific research requires systems to pursue multiple interdependent claims through…
- arXiv cs.AIresearchOne-Sided Verification Under Limited Expert Review
arXiv:2610.18089v2 Announce Type: replace Abstract: AI has become increasingly helpful in scientific discovery, yet human expert review remains essential for those problems without reliable automated evaluation, posing a…
- arXiv cs.AIagentsAM-Bench: Understanding Agents under Task Underspecification across Models and Harnesses
arXiv:2610.18090v1 Announce Type: new Abstract: Ambiguous or incomplete task specifications complicate both execution and clarification for language-model agents. Yet agents' responses to these information gaps remain po…
- arXiv cs.AIagentsLifeSearch: Benchmarking Deep Research Agents for Real-World Life and Productivity
arXiv:2610.18092v1 Announce Type: new Abstract: Deep research (DR) agents address open-ended information needs through multi-step reasoning, long-horizon web search, and evidence synthesis. However, existing benchmarks p…
- arXiv cs.AIresearchCompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions
arXiv:2610.18095v1 Announce Type: new Abstract: AI companions provide users with emotional support and ongoing companionship, but their sustained relational interactions also introduce distinct safety risks. Prior work l…
- arXiv cs.AIresearchChain of Thought Monitoring Can Fail Even When CoT Is Necessary
arXiv:2610.18105v1 Announce Type: new Abstract: Chain of Thought (CoT) monitoring is used by frontier labs to detect misbehaviour of AI systems. Yet, its reliability remains poorly understood. We attribute this to the la…
- arXiv cs.AIresearchFresh at Decision, Stale at Action: Routing New Information to LLM Decisions Already Made
arXiv:2610.18126v1 Announce Type: new Abstract: Freshness shapes an LLM decision at the moment it is made; the action it commits to is latent, carried out later, in a changing world. We therefore introduce a timestamp th…
- arXiv cs.AIresearchMonitoring latent reasoning in looped language models
arXiv:2610.18127v1 Announce Type: new Abstract: Looped language models (LMs) reuse one block of layers several times per token generation, promising more latent computation at no additional storage cost. Despite their ri…
- arXiv cs.AIresearchMitigating Cross-Modal Hallucinations by Correcting Modality Misrouting in Omnimodal LLMs
arXiv:2610.18141v1 Announce Type: new Abstract: Omnimodal large language models (OLLMs) are susceptible to cross-modal hallucinations under audio-visual interference. We find that, for a substantial fraction of incorrect…
- arXiv cs.AIresearchRadixFlow: Filling Execution Bubbles in Prefix-Cached Hybrid LLM Serving
arXiv:2610.18143v1 Announce Type: new Abstract: Prefix reuse improves LLM inference by sharing the KV cache of common prompt prefixes. This helps only if the scheduler can execute a matched branch in the current worker r…
- arXiv cs.AIagentsWhen and How Order-Flow Interventions Work After Dealers Adapt
arXiv:2610.18158v1 Announce Type: new Abstract: Learning dealer agents can settle on persistently wide quotes, raising what customers pay to trade. A venue can route more orders to tighter quotes, but a wide quote may re…
- arXiv cs.AIresearchBack to the Future: Reverse-Consequence Modeling for Long-Horizon Particle Dynamics
arXiv:2610.18168v1 Announce Type: new Abstract: Accurate prediction of object trajectories is fundamental to mechanical understanding and robotic control. However, autoregressive models inherently suffer from cumulative…
- arXiv cs.AIagentsNeuro-Symbolic Graph Transformers for Hierarchical Intention Recognition from Multimodal Human Activity Sequences
arXiv:2610.18176v1 Announce Type: new Abstract: Proactive human-robot collaboration requires autonomous systems to infer not only immediate actions but also the underlying hierarchical intentions governing human behavior…
- arXiv cs.AIresearchQORH: Learning Query-Specific Ordered Rule Hypergraphs for Inductive Knowledge Graph Link Prediction
arXiv:2610.18198v1 Announce Type: new Abstract: Knowledge graph link prediction involving unseen entities and relations requires learning transferable reasoning patterns from observed graph structure. Existing methods ba…
- arXiv cs.AIresearchConsider, Then Choose: Order-Invariant Decisions in System One Models
arXiv:2610.18233v1 Announce Type: new Abstract: System One models answer typed questions in a single forward pass and promise the same answer for the same input. For choice questions, this promise fails: the answer depen…
- arXiv cs.AIagentsBeyond Answer Sharing: TrueMAD for Targeted Peer Engagement in Multi-Agent Debate
arXiv:2610.18240v1 Announce Type: new Abstract: Multi-agent debate (MAD) aims to improve large language model reasoning by exposing agents to alternative solutions and enabling iterative revision. However, standard broad…
- arXiv cs.AIagentsOutput Discipline Sets the Floor: A Falsification-Guided, Model-Agnostic Agent Protocol for Auditable Hypothesis-Driven Decision Making
arXiv:2610.18298v2 Announce Type: replace Abstract: What binds large language models on auditable, hypothesis-driven decision tasks, where every candidate can be checked against the evidence? On the public TCMEval-SDT be…
- arXiv cs.AIresearchA dataset of formalised theorem statements from the Annals of Mathematics
arXiv:2610.18301v1 Announce Type: new Abstract: Recent progress in autoformalisation of mathematics using AI has been impressive. Measuring this progress requires datasets of formal statements that are both hard and trus…
- arXiv cs.AIresearchEfficient Safety Guardrails through Latent Dual-Hypothesis Reasoning with On-Demand Trace Reconstruction
arXiv:2610.18304v1 Announce Type: new Abstract: Guardrail approaches that rely on reasoning-based large language models (LLM) improve safety decisions, but come with substantial inference overhead due to the explicit rea…
- arXiv cs.AIresearchComplex materials engineering via Provenance Action Graphs: potential, structure and demonstration
arXiv:2610.18314v1 Announce Type: new Abstract: This work discusses and tests the potential of reaction graphs for material synthesis, in which events consist of reaction steps (actions) and their outputs (observations).…
- arXiv cs.AIagentsAssetForge: Asset-Augmented Task Synthesis for Business Automation Agents
arXiv:2610.18330v2 Announce Type: replace Abstract: Training business automation agents requires executable tasks that connect a natural-language request to an application state and a verifiable end state. Traditional Ru…
- arXiv cs.AIagentsChoosing LLMs for Strategic Agent Interactions
arXiv:2610.18354v1 Announce Type: new Abstract: Game-theoretic benchmarks claim that large language model (LLM) strategic decision-making varies across game types, interaction structures, and capability dimensions. Howev…
- arXiv cs.AIagentsABot-ER: Unified Embodied Reasoning through Agentic Data-Model Co-Evolution
arXiv:2610.18355v2 Announce Type: replace Abstract: We introduce ABot Embodied Reasoning (ABot-ER), a unified embodied reasoning foundation model that breaks the tension between breadth and depth in embodied reasoning. E…