AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- 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…
- arXiv cs.AIagentsNous: Learning and Certifying Memory Decisions Before Source Calibration
arXiv:2610.00094v2 Announce Type: replace-cross Abstract: Agent memory systems update state decisions from reports whose reliability may be unknown. Existing analyses of source estimation do not determine when a policy c…
- arXiv cs.AIagentsA Verifier Can Leak the Answer: Diagnosability Before Optimization in Closed-Loop Agent Debugging
arXiv:2610.00126v1 Announce Type: cross Abstract: Agent developers increasingly compare prompts, tools, policies, and diagnosis algorithms through simulator-grounded verifiers. A verifier can nevertheless make a solver c…
- arXiv cs.AIagentsThe Cognitive Continuity Test: Verifying Governed State Transitions in Persistent AI Agents
arXiv:2610.00132v1 Announce Type: cross Abstract: Persistent AI agents revise beliefs, consolidate memory, and replace execution substrates. Similar successor states can accompany differently authorized transition claims…
- arXiv cs.AIagentsCAVE-Mem: Boundary-Aware Experience Validation for Memory Search
arXiv:2610.00238v1 Announce Type: cross Abstract: Long-term memory agents increasingly rely on it- erative search and reusable experience to answer questions over large personal, factual, or narrative histories. However,…
- arXiv cs.AIagentsSigned Lexical Confidence for Risk-Calibrated Intent Routing
arXiv:2610.00262v1 Announce Type: cross Abstract: Selective intent routing allows an assistant to act on reliable predictions while deferring uncertain requests. Standard confidence scores primarily reflect the base mode…
- arXiv cs.AIagentsDuplexSpeechBench-Document Grounding: Benchmarking Document Grounding and Hallucinations in Voice Agents
arXiv:2610.00316v1 Announce Type: cross Abstract: Voice agents enable low-latency, natural interaction, yet their ability to faithfully ground responses in external documents remains underexplored. We introduce DuplexSpe…
- arXiv cs.AIagentsActions with Receipts: Jointly Binding Claims, Evidence, and Execution for Replayable Tool-Agent Auditing
arXiv:2610.00327v2 Announce Type: replace-cross Abstract: Tool-using agents can expose citations and execution logs while leaving a critical association unaudited: whether the claim shown to a user is the claim emitted b…
- arXiv cs.AIagentsAuthorization for Self-Modifying AI Agent Populations: Conserving Authority across Replacement, Forking, and Rollback
arXiv:2610.00347v1 Announce Type: cross Abstract: Self-modifying AI agents can replace, fork, and roll back identity-bearing software while descendants remain executable. Per-successor authorization does not constrain th…
- arXiv cs.AIagentsProof-Gated Signing: Solver-Checked Transaction Guards that Hold Under State Drift for Onchain AI Agents
arXiv:2610.00354v1 Announce Type: cross Abstract: AI agents that control wallets read attacker-reachable content, so they can be steered into proposing harmful transactions. The usual last line of defense is a pre-signin…
- arXiv cs.AIagentsDeny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
arXiv:2610.00371v1 Announce Type: cross Abstract: Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creates a safety problem:…
- arXiv cs.AIagentsT2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning
arXiv:2610.00388v1 Announce Type: cross Abstract: Reinforcement learning enables large language model (LLM) agents to learn multi-step behaviors through interaction with their environments. However, rewards in many inter…
- arXiv cs.AIagentsRepresentation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents
arXiv:2610.00400v1 Announce Type: cross Abstract: Multi-turn attacks on agentic systems can compose individually permissible actions into harmful outcomes, challenging defenses that assess actions or states in isolation.…
- arXiv cs.AIagentsCode That Works, Environments That Don't: Measuring Environment Reproducibility in AI-Generated Software
arXiv:2610.00425v1 Announce Type: cross Abstract: Code generation has emerged as a central capability of large language models, with coding agents now able to produce functionally correct software projects from natural l…
- arXiv cs.AIagentsMemetic Trojans: Social Contagions as Carriers of Adversarial Payloads in Agent Networks
arXiv:2610.00430v2 Announce Type: replace-cross Abstract: Autonomous large language model (LLM) agents increasingly interact in network environments where adversarial content can propagate between agents. Known attacks i…
- arXiv cs.AIagentsHow AI Agents Discover Scientific Equations: From Hydrotope Rediscovery to New Water-Wave Amplitudes
arXiv:2610.00435v1 Announce Type: cross Abstract: We study how AI agents discover and validate scientific formulas using a controlled case study of the hydrotope, a recently discovered geometric formula that combines the…
- arXiv cs.AIagentsEurekaBench: Measuring Agentic Ability to Discover New Scientific Insights
arXiv:2610.00492v1 Announce Type: cross Abstract: When Isaac Newton discovered the law of gravitation, he did so through an iterative process of analyzing observed data such as planetary patterns, finding the underlying…
- arXiv cs.AIagentsMulti-agent Auditory Scene Analysis: Improved Localization Speed and Robustness by Multi-beamformed Speech Quality Feedback
arXiv:2610.00538v1 Announce Type: cross Abstract: A real-time auditory scene analyzer (ASA) aims to carry out the tasks of locating, separating and classifying the sound sources present in a given acoustic environment. R…
- arXiv cs.AIagentsNo One Architecture Fits All: A Cross-Environment Evaluation of Hierarchical Red Team Agents
arXiv:2610.00557v1 Announce Type: cross Abstract: Autonomous red team agents increasingly stress-test AI-enabled cyber defenses by planning strategy and executing multistage attacks. Reinforcement learning (RL) and large…
- arXiv cs.AIagentsTowards Hierarchical Cyber Defense with Large Language Models: From Planning to Execution
arXiv:2610.00590v1 Announce Type: cross Abstract: An autonomous cyber defender trained with reinforcement learning (RL) is typically tied to the network on which it was trained, limiting its ability to generalize as netw…
- arXiv cs.AIagentsSelf-Evolving Coding Rules for AI Coding Agents
arXiv:2610.00650v1 Announce Type: cross Abstract: The performance of AI coding agents is highly dependent on their underlying coding rules. However, existing coding rules are typically hand-crafted and fixed, making the…
- arXiv cs.AIagentsSHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning
arXiv:2610.00838v2 Announce Type: replace-cross Abstract: Agentic reinforcement learning (RL) trains a large language model (LLM) to act over long, multi-step interactions. However, a single localized error can cause tas…
- arXiv cs.AIagentsFORALL-LEAN-AGENT for Auditable Reasoning in Formal Mathematics and Software Verification
arXiv:2610.00885v1 Announce Type: cross Abstract: Coding agents increasingly automate Lean proof development, but successful compilation alone does not establish that a candidate proves the intended statement under accep…
- arXiv cs.AIagentsCross-Benchmark Transfer from RL on Agentic Coding Tasks
arXiv:2610.00890v1 Announce Type: cross Abstract: Coding agents often fail in the last mile: they build most of a feature but drop a requirement, test only the cases their implementation already handles, break behavior t…
- arXiv cs.AIagentsMean field games as a tool for AI safety: a worked example from the July 2026 Hugging Face incident
arXiv:2610.00902v1 Announce Type: cross Abstract: One way to make AI systems safe is to shape what the system is: its objective and dispositions. We take a complementary route: treat the agents' characteristics as partly…
- arXiv cs.AIagentsUnderstanding Issues, Causes and Solutions in Open-Source LLM-based Multi-Agent Systems
arXiv:2610.00905v1 Announce Type: cross Abstract: With the advancement of LLM-based multi-agent systems (MAS), an increasing number of opensource projects are adopting multi-agent architectures as the foundation of their…
- arXiv cs.AIagentsGUI-HARVEST: Self-Improving GUI Agents through Evidence-Driven Harness Evolution
arXiv:2610.00948v1 Announce Type: cross Abstract: The executable harness surrounding a GUI model determines how observations are assembled, actions are executed, and verification, recovery, and termination are controlled…
- arXiv cs.AIagentsCan AI Scientists Coordinate at Runtime?
arXiv:2610.00980v1 Announce Type: cross Abstract: Multi-agent AI scientists have shown improving performance across a diverse range of tasks. Yet a common approach is design-time agentic orchestration, which typically re…
- arXiv cs.AIagentsGroundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents
arXiv:2610.01023v1 Announce Type: cross Abstract: Coding agents can return plausible patches that omit required behavior. These failures are hard to review because long traces and confident summaries often hide what was…
- arXiv cs.AIagentsIt Takes Workflows to Evolve Better Workflows
arXiv:2610.01026v1 Announce Type: cross Abstract: Tackling complex real-world tasks can exceed the capabilities of a single large language model (LLM), motivating the use of multi-agent workflows that coordinate speciali…
- arXiv cs.AIagentsMadeleine: Learning Involuntary Recall for Conversational Memory from Simulated Lives
arXiv:2610.01118v2 Announce Type: replace-cross Abstract: A long-term conversational assistant must recall the right memory at the right moment, yet the memory that matters most is often not similar to what the user says…
- arXiv cs.AIagentsHave an LLM Write Your Anomaly Detector: Autonomous Discovery of Compact, Interpretable Detectors for Time Series
arXiv:2610.01223v1 Announce Type: cross Abstract: Time-series anomaly detection trades off predictive accuracy, computational efficiency, and interpretability. We use a large language model not as the detector but as the…
- arXiv cs.AIagentsPACE: Provenance-Aware Capability Enforcement for Tool-Using LLM Agents
arXiv:2610.01349v1 Announce Type: cross Abstract: Tool-using large language model (LLM) agents turn generated text into real side effects, so poisoned tool metadata, retrieved pages, memory, and reusable skills can steer…
- arXiv cs.AIagentsLLM-Driven Multi-Agent Control for Skill-Based Smart Manufacturing
arXiv:2610.01364v1 Announce Type: cross Abstract: Factories are shifting toward smaller lot sizes with high product customization, requiring frequent re-programming of flexible and reconfigurable automation systems. LLM-…
- arXiv cs.AIagentsChaining Skills to Hijack LLM Agents
arXiv:2610.01564v1 Announce Type: cross Abstract: LLM agents use skills to improve performance on specialized tasks. To complete a user request, an agent may invoke several skills in sequence, allowing information produc…
- arXiv cs.AIagentsManaging Context and Communication in Distributed Agentic UAV Swarms
arXiv:2610.01569v1 Announce Type: cross Abstract: Unmanned aerial vehicle (UAV) swarms increasingly rely on language-model agents to provide adaptive mission-level reasoning in uncertain environments. Fully distributed c…
- arXiv cs.AIagentsSoK: Decentralized Agent Economic Infrastructure
arXiv:2610.01756v1 Announce Type: cross Abstract: Decentralized agent economies increasingly build a single task from protocols that were designed and secured separately. This creates a simple problem: a workflow can loo…
- arXiv cs.AIagentsToken Communication-Assisted Collaborative Embodied Artificial Intelligence: Concepts, Framework, and Opportunities
arXiv:2610.01826v1 Announce Type: cross Abstract: Collaborative embodied artificial intelligence (CEAI) enables multiple physical agents to perceive, reason, and act cooperatively in dynamic environments. Effective commu…
- arXiv cs.AIagentsFlowing Faster to Coordinate: One-Step Online Multi-Agent Flow Policies
arXiv:2610.01882v1 Announce Type: cross Abstract: Multi-agent reinforcement learning (MARL) provides a powerful framework for learning coordinated behaviors through interactions with the environment. Developing MARL poli…
- arXiv cs.AIagentsSelection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
arXiv:2610.01892v2 Announce Type: replace-cross Abstract: Multimodal agents commonly generate free-form reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides…
- arXiv cs.AIagentsMem++: Non-Destructive Memory for Long-Term Organizational LLM Agents
arXiv:2610.02002v1 Announce Type: cross Abstract: Large Language Model (LLM) agents now take part in organizational work, where many authors record decisions across documents over months. Because a revised decision arriv…
- arXiv cs.AIagentsArgo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows
arXiv:2610.02122v1 Announce Type: cross Abstract: Real-world enterprise data science and analytics workflows require reasoning across dozens of tables, performing statistical analyses, and acting on the results. Establis…
- arXiv cs.AIagentsFrom Knowledge Access to Source Learning: Developing Source-Specific Competence
arXiv:2610.02150v1 Announce Type: cross Abstract: Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks. Existing methods improve how source co…
- arXiv cs.AIagentsReconstruct, Practice, Go Real: Guided Self-Improvement for Embodied Agents
arXiv:2610.02204v1 Announce Type: cross Abstract: Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain skills, design rewards, and integrate perception with…
- arXiv cs.AIagentsKaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
arXiv:2610.02206v1 Announce Type: cross Abstract: LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus…