AI news archive.
4,959 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsWorse Together: How Performance Breaks Down in Multi-User Multi-Agent Teams
arXiv:2610.00583v1 Announce Type: new Abstract: People are increasingly delegating tasks to AI agents, and those agents are increasingly encountering other people's agents over shared resources such as a codebase, a cale…
- arXiv cs.AIagentsLegal Research Bench: Measuring End-to-End Reliability in Long-Horizon Legal Research Agents
arXiv:2610.00609v1 Announce Type: new Abstract: Legal research is a core and time-consuming legal workflow. Lawyers must identify controlling authority, verify that it remains valid, reconcile statutes and cases, and syn…
- arXiv cs.AIagentsSpatial Strategies, Not Actions: Vector-Quantized Geodesics as Tools for LLM-Driven Agents
arXiv:2610.00613v1 Announce Type: new Abstract: Large language model (LLM) based agents are often criticized for lacking spatial understanding and mainly exploiting statistical text patterns. We investigate their spatial…
- arXiv cs.AIagentsCompMat-Bench: Benchmarking AI Agents for Computational Materials Science
arXiv:2610.00636v2 Announce Type: replace Abstract: Evaluating AI agents on scientific research tasks is constrained by the time and resources required for the underlying experiments or calculations. In computational mat…
- arXiv cs.AIagentsIncident-Arena: Getting agents to the last nine of reliability
arXiv:2610.00648v1 Announce Type: new Abstract: AI coding agents are ubiquitous in engineering workflows amongst industry and academia. Yet, despite their use in app coding, relatively less attention has been paid to the…
- arXiv cs.AIagentsAgent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard
arXiv:2610.00651v1 Announce Type: new Abstract: Agent evaluations are increasingly used to compare LLMs and inform deployment decisions, yet ranks can reflect not only the model but also the effects of the evaluation con…
- arXiv cs.AIagentsA Simple Doxastic Deontic Logic for Norm-Guided Decision Making
arXiv:2610.00668v1 Announce Type: new Abstract: Making decisions despite conflicting norms and incomplete or unreliable information is a fundamental challenge for autonomous systems. We introduce a simple doxastic deonti…
- arXiv cs.AIagentsMeta-Multi-Agent Reinforcement Learning for Fast Adaptation of Interactive Policies with Applications to Autonomous Driving
arXiv:2610.00705v1 Announce Type: new Abstract: This paper develops a meta-multi-agent reinforcement learning (meta-MARL) framework to enable fast adaptation of interactive policies in a multi-agent system (MAS). Meta-re…
- arXiv cs.AIagentsReLiveGym: Evaluating Long-Lived Agents over Weeks of Replayed Reality
arXiv:2610.00710v1 Announce Type: new Abstract: As large language model (LLM) agents become widely adopted, they are increasingly deployed for tasks that require persistent monitoring or recurring actions (e.g., market a…
- arXiv cs.AIagentsSapien: A Stateful Policy Engine for Autonomous AI Agents
arXiv:2610.00797v1 Announce Type: new Abstract: Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool calls. In multi-step ta…
- arXiv cs.AIagentsKepler: Auditable World Models for ARC-AGI-3
arXiv:2610.00834v1 Announce Type: new Abstract: ARC-AGI-3 evaluates agents in interactive environments whose rules and objectives must be inferred from observation. We present Kepler, an open-source harness that represen…
- arXiv cs.AIagentsAn Educator-Guided LLM Pedagogical Agent for Scaffolded Feedback in Conceptual Database Design
arXiv:2610.00870v1 Announce Type: new Abstract: We present an educator-guided LLM pedagogical agent for scaffolded feedback in conceptual database design. Integrated into an entity--relationship diagram (ERD) editor, the…
- arXiv cs.AIagentsMemFit: Efficient Long-Term Agentic Memory
arXiv:2610.00872v1 Announce Type: new Abstract: Long-term memory systems for large language models (LLMs) have gained popularity for extending reasoning capabilities across applications. Current memory systems rely on LL…
- arXiv cs.AIagentsActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization
arXiv:2610.00906v1 Announce Type: new Abstract: Automated harness optimization can substantially improve LLM agents by iteratively updating their prompts, tool interfaces, and control logic from execution feedback. Howev…
- arXiv cs.AIagentsFinding the Right Fit: Model-Harness Interactions across Agent Tasks
arXiv:2610.00917v1 Announce Type: new Abstract: Choosing an agent system means choosing both a language model and the harness through which it acts. We ask whether a strong model, harness, or pairing stays strong when th…
- arXiv cs.AIagentsPG-SFT: Balancing Capability Acquisition and Retention in Offline Agent Fine-Tuning
arXiv:2610.00949v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) on offline agent trajectories is the standard approach for training specialized tool-using agents, but forcing models to imitate reasoning and…
- arXiv cs.AIagentsCybernetic and Epistemic: A Missing Vocabulary for Trustworthy Agentic Delegation
arXiv:2610.00961v1 Announce Type: new Abstract: As code generation is increasingly delegated to AI systems, the bottleneck is shifting from writing code to supervising the systems that write it --- a shift CS-education r…
- arXiv cs.AIagentsVeriHarness: Scaling Agentic Verification for Long-Horizon Tasks
arXiv:2610.00972v1 Announce Type: new Abstract: As LLM agents undertake increasingly complex, long-horizon tasks, verifying their outputs becomes increasingly challenging. We study how verification capability can be stre…
- arXiv cs.AIagentsRISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation
arXiv:2610.00979v1 Announce Type: new Abstract: Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing curriculum and data…
- arXiv cs.AIagentsPay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization
arXiv:2610.01017v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly construct multi-agent workflows that decompose a complex task and assign specialist agents from a pool. However, building such…
- arXiv cs.AIagentsBeyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems
arXiv:2610.01042v1 Announce Type: new Abstract: Multi-agent communication aims to help agents benefit from one another's information. Yet improvements in system performance leave a fundamental ambiguity: do they reflect…
- arXiv cs.AIagentsEmpty Commitments: When Agents Promise What They Cannot Deliver
arXiv:2610.01045v2 Announce Type: replace Abstract: A chatbot that says "I will remind you tomorrow" will not run again until the user writes. We call such a promise an empty commitment: a promise of action after the cur…
- arXiv cs.AIagentsYouRA: A Persistent-State Architecture for Evidence-Traceable Autonomous Research Agents
arXiv:2610.01097v1 Announce Type: new Abstract: End-to-end research agents can now produce complete scientific papers, yet manuscript claims often diverge from executed experiments. This gap is structural: research state…
- arXiv cs.AIagentsAbsorbEvo: An Agentic Framework for Autonomous Inverse Design of Microwave Absorbers
arXiv:2610.01119v1 Announce Type: new Abstract: Designing high-performance microwave absorbers requires specialized expertise in electromagnetic theory, materials science and simulation programming, and entails time-cons…
- arXiv cs.AIagentsAuditing Action Settlement in LLM Agent Environments: Order, Progress, and Replay
arXiv:2610.01138v1 Announce Type: new Abstract: Concurrent actions in large language model (LLM) agent environments require arbitration even when each proposal is individually valid. We implement a typed snapshot-settlem…
- arXiv cs.AIagentsFederated Agent Optimization
arXiv:2610.01195v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate in private environments and accumulate valuable experience from task execution, tool use, feedback, and local knowled…
- arXiv cs.AIagentsDependency-Aware Reward Shaping for Agentic Reinforcement Learning
arXiv:2610.01207v1 Announce Type: new Abstract: When training large language models with reinforcement learning, terminal rewards provide little guidance about which steps matter. Common methods for assigning step credit…
- arXiv cs.AIagentsReputation, Strategy, and Emotion Effects on Generative AI Cooperation: A Comparison Across Reasoning and Non-Reasoning Models
arXiv:2610.01222v1 Announce Type: new Abstract: As generative AI (Gen AI) systems take on increasingly autonomous roles in economically and socially consequential interactions, understanding their propensity to cooperate…
- arXiv cs.AIagentsRevision-Aware Independent Agent Graphs for Dynamic Reasoning
arXiv:2610.01249v1 Announce Type: new Abstract: Conventional reasoning protocols present a fixed, preselected task, so they cannot test whether an agent propagates relevant updates, preserves unaffected work, or reconstr…
- arXiv cs.AIagentsDeFA: Dependency-Guided Failure Attribution for LLM Agents
arXiv:2610.01256v1 Announce Type: new Abstract: Errors in LLM agent executions and their visible consequences can be separated by many steps, making decisive-error localization a matter of understanding both step content…
- arXiv cs.AIagentsSCOPE-AD: Sequential cost-aware ordinal-belief planning with energy-based models for diagnostic agents
arXiv:2610.01278v1 Announce Type: new Abstract: Alzheimer's disease (AD) diagnosis requires sequential evidence acquisition under heterogeneous test costs and patient burden. Fixed-modality predictors do not jointly deci…
- arXiv cs.AIagentsVerify Claims, Not Scores: Evidence-Based Verification of Modular Agents
arXiv:2610.01348v1 Announce Type: new Abstract: When developers change one component of an agent, such as its controller, a learned model or its verifier, they usually judge the change by an aggregate task score. That sc…
- arXiv cs.AIagentsBeyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States
arXiv:2610.01415v1 Announce Type: new Abstract: Large language model (LLM) agents can now undertake increasingly complex tasks, but the way they organize interaction history into memory does not ensure a coherent underst…
- arXiv cs.AIagentsA Multi-Agent LLM Framework for Personalized Health Checkup Interpretation and Guidance
arXiv:2610.01451v1 Announce Type: new Abstract: Personalized interpretation of health checkup results requires reasoning across longitudinal records, medical knowledge, lifestyle guidance, and healthcare navigation. We p…
- arXiv cs.AIagentsOpenMTB-Audit: Exposing Over-Refusal and Clinical Expert Perspectives in LLM-Based Molecular Tumor Board Safety Evaluation
arXiv:2610.01497v1 Announce Type: new Abstract: Molecular tumor boards integrate genomic findings, clinical context, and therapeutic evidence to support precision oncology. As AI enters this workflow, a key safety challe…
- arXiv cs.AIagentsMCRI: A Four-Dimensional Framework for Analyzing and Evaluating Agent Skills
arXiv:2610.01506v1 Announce Type: new Abstract: As agents evolve from single-tool systems into modular, composite architectures, skills are becoming an important mechanism for capability development and distribution. How…
- arXiv cs.AIagentsTowards Reliable Vision-Language Models for Autonomous Driving
arXiv:2610.01531v1 Announce Type: new Abstract: Vision-Language models (VLMs) are increasingly being explored in autonomous driving for tasks such as scene understanding, driving reasoning, decision-making, and end-to-en…
- arXiv cs.AIagentsEvaluating Physical Consistency and Plausibility in Generative Scenario Models for Autonomous Driving
arXiv:2610.01581v1 Announce Type: new Abstract: Generative AI models are increasingly used for scenario generation in autonomous driving. While they can generate realistic-looking scenarios, they often provide limited tr…
- arXiv cs.AIagentsAgents Are Systems, Not Models: Rethinking Agentic Evaluation
arXiv:2610.01618v1 Announce Type: new Abstract: Agent evaluations increasingly go beyond a single success rate, reporting metrics such as cost, consistency, and robustness. Yet they typically treat the agent itself as fi…
- arXiv cs.AIagentsVideoEvolve: Evolving Agent Harnesses for Video Temporal Grounding
arXiv:2610.01766v1 Announce Type: new Abstract: Video temporal grounding aims to localize events in videos from natural-language queries. For agents built around frozen video-language models, the harness determines how q…
- arXiv cs.AIagentsNot All Experience Belongs in the Weights: Component Routing for Self-Improving GUI Agents
arXiv:2610.01787v1 Announce Type: new Abstract: Self-improving GUI agents keep the trajectories they produce and return them to the agent, by fine-tuning or by retrieval into the prompt, and studies that compare the two…
- arXiv cs.AIagentsContinuous Process-Level Evaluation for Evolving Enterprise AI Agent Skills
arXiv:2610.01833v1 Announce Type: new Abstract: Enterprise AI agent skills evolve as tool APIs, models, and specifications change, yet final-output evaluation can miss process-level behavioral drift. We present a continu…
- arXiv cs.AIagentsCode Owns the Simulation, Jev Owns the Evaluation
arXiv:2610.01834v2 Announce Type: replace Abstract: Judgment models such as \jev{} return, in a single call and without reasoning text, a probability for each described option. This makes them attractive as an agent's ac…
- arXiv cs.AIagentsMingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks
arXiv:2610.02001v1 Announce Type: new Abstract: Small open-weight models (2-9B) run on ordinary laptops, but under cloud-scale agent harnesses they rarely complete real tasks: tool prefill overflows the context, self-cor…
- arXiv cs.AIagentsGlobal Coherence: When Every Agent Is Right and the Team Is Still Wrong - A Local-to-Global Semantic Foundation for Multi-Agent Collaboration
arXiv:2610.02036v2 Announce Type: replace Abstract: AI agents can each make locally valid decisions yet jointly produce an invalid result. We call this the global coherence problem: a failure of shared state, not merely…
- arXiv cs.AIagentsMimir: Physics-Grounded LLM Agents for Long-Horizon Irrigation Control
arXiv:2610.02038v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly combine reasoning, tool use, and action, but most evidence comes from episodic tasks with relatively immediate feedback and r…
- arXiv cs.AIagentsPyPottery: an AI-powered end-to-end suite for pottery processing and publication
arXiv:2610.02072v1 Announce Type: new Abstract: The study of ceramic materials constitutes a cornerstone of archaeological research, yet the post-production workflow for pottery documentation remains labor-intensive and…
- arXiv cs.AIagentsThe Delegation Danger Band: Why Mid-Capability Sub-Agents Over-Trust Inherited Stale State
arXiv:2610.00041v1 Announce Type: cross Abstract: Agent frameworks increasingly delegate work by forking sub-agents; a common default makes the child inherit the parent's full working context. We measure how the effect o…
- arXiv cs.AIagentsBudgetSchemaBench: A Budget-Swept Diagnostic for Schema Context in Text-to-SQL
arXiv:2610.00092v1 Announce Type: cross Abstract: Data agents over structured sources must fit database schema into the model's context window. Large catalogs can span many databases and thousands of columns, so cost con…
- arXiv cs.AIagentsSafety in Self-Evolving Agents: A Survey
arXiv:2610.00093v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong general capabilities, yet their parameters typically remain fixed after deployment, limiting learning from new interactions. I…