AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsVisual Grounding Safety in Vision-Language Models
arXiv:2610.05637v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly trained to generate structured outputs like points and bounding boxes that downstream interfaces, agents, and robots can act…
- arXiv cs.AIagentsSecond-Order Problem Solving for Recursive Self-Improvement in Formal Verification
arXiv:2610.05701v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) enables agents to iteratively optimize their workflows via execution feedback. However, standard RSI typically operates as a first-orde…
- arXiv cs.AIagentsMining Agent Skills from Production Traces
arXiv:2610.05777v1 Announce Type: new Abstract: Agent skills that record procedural instructions are increasingly mined from execution traces rather than curated by hand. Skill-mining pipelines often use known task outco…
- arXiv cs.AIagentsAgentic-ZTA: A Multi-Agent Architecture for Autonomous Zero Trust Enforcement
arXiv:2610.05782v1 Announce Type: new Abstract: Agentic AI is emerging as a promising paradigm for automating complex cybersecurity decisions, yet its use in enforcing zero trust introduces significant challenges in safe…
- arXiv cs.AIagentsTopology-Conditioned Backdoors: Language Models That Insert Vulnerabilities When They Infer They Are in a Multi-Agent System
arXiv:2610.05793v1 Announce Type: new Abstract: A language model may behave safely in a single-agent evaluation yet produce vulnerable code when its context suggests that it is part of a multi-agent system. We study this…
- arXiv cs.AIagentsMeasurement-First Auditing of Agentic Leaderboards: Contamination Susceptibility, Matched-Control Re-evaluation, and Scorer Validation
arXiv:2610.05830v1 Announce Type: new Abstract: Agentic leaderboards increasingly evaluate systems on public benchmarks whose task statements and solution-bearing artifacts can remain accessible. We propose a measurement…
- arXiv cs.AIagentsRequest Order Matters: Cache-History Sensitivity in Selective KV-Cache Reuse for Rolling Agents
arXiv:2610.05833v1 Announce Type: new Abstract: Long-running agents repeatedly call an LLM while retaining most of their document window, evicting old documents, and appending new ones. These rolling updates break exact…
- arXiv cs.AIagentsMiniCorp: The Last Mile to an AI Agent Corporation
arXiv:2610.05912v2 Announce Type: replace Abstract: The last mile toward enterprise AGI is a company that runs itself. Training and adapting such agents require longitudinal enterprise data, which remain scarce, costly t…
- arXiv cs.AIagentsVERA: Scaling Verifiable Environments for Agentic co-Evolution
arXiv:2610.05923v1 Announce Type: new Abstract: Competent agents need precise and verifiable environments, such as sandboxes that are resumable at any stage and evolve from observable evidence. However, most long-horizon…
- arXiv cs.AIagentsProcess Constitutions and Process Stewards: Towards the Next Generation of BPM for Agentic Organizations
arXiv:2610.05942v1 Announce Type: new Abstract: Business Process Management (BPM) was built on a foundational assumption that organizations are populated primarily by human actors whose work can be made visible, governab…
- arXiv cs.AIagentsOntoInk: Interactive Ontology Visualization, Validation, and Reasoning
arXiv:2610.05945v1 Announce Type: new Abstract: Ontology documentation, visualization, and validation are usually carried out with separate tools. This split workflow slows down development and makes knowledge transfer h…
- arXiv cs.AIagentsRocketAgent: A Long-Horizon Engineering Agent for Multidisciplinary Design of Liquid-Rocket Thrust Chambers
arXiv:2610.06044v2 Announce Type: replace Abstract: Liquid-rocket thrust-chamber design involves interdependent analyses in which downstream constraints can require earlier design decisions to be revisited. Managing thes…
- arXiv cs.AIagentsBenchmarking Jailbreak Guardrails for Embodied Agents
arXiv:2610.06122v1 Announce Type: new Abstract: Embodied agents powered by large language models and vision-language models are increasingly deployed in physical environments, but jailbreak attacks can induce these agent…
- arXiv cs.AIagentsBridging the Evidence-to-Execution Gap:A Reflective Agent for Multi-Objective Peptide Design
arXiv:2610.06190v1 Announce Type: new Abstract: Large language models (LLMs) can reason over scientific literature to devise design strategies, yet fail to reliably implement them for biological sequences. While protein…
- arXiv cs.AIagentsJudged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions
arXiv:2610.06191v1 Announce Type: new Abstract: An agent whose tool keeps returning nothing useful should stop relying on it. In a retrieval environment with controlled source failures, we separate how agents judge resul…
- arXiv cs.AIagentsCopies or Sources? Measuring How LLM Aggregators Count Restated Evidence in Multi-Agent Systems
arXiv:2610.06192v1 Announce Type: new Abstract: Multi-agent systems built on large language models (LLMs) restate observations as a matter of course: relays forward them, shared boards repeat them and discussion rounds e…
- arXiv cs.AIagentsDo Small Language Models Learn to Negotiate? A Controlled Scaling Study of RL-Trained Sellers
arXiv:2610.06204v1 Announce Type: new Abstract: LLM agents are starting to own the full customer experience. Soon, LLMs may be selling and buying on behalf of companies and customers respectively. Small models are more c…
- arXiv cs.AIagentsAI-Decision Checkpoints for AI-Augmented Business Process Management: Framework and Educational Instantiation
arXiv:2610.06207v1 Announce Type: new Abstract: Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and AI agents are increasingly embedded in operational business processes. Yet Business Process Manageme…
- arXiv cs.AIagentsCRAFTER: Causality-based Self-adaptation for Autonomous IoT Systems
arXiv:2610.06320v1 Announce Type: new Abstract: This paper presents CRAFTER, an automated framework for designing and deploying self-adaptive IoT systems using Causal Reinforcement Learning (CRL). As IoT devices increasi…
- arXiv cs.AIagentsImproveAnyTask: An Autonomous Post-Training Harness for Iterative Model Self-Improvement
arXiv:2610.06347v1 Announce Type: new Abstract: Adapting general-purpose large language models to specific tasks requires substantial human effort in designing data and training strategies. Sustaining improvement is espe…
- arXiv cs.AIagentsCapability-Driven Self-Evolution of Agent Memory
arXiv:2610.06361v1 Announce Type: new Abstract: Memory self-evolution uses task feedback to iteratively improve executable memory programs that store and retrieve information from past interactions. Existing approaches t…
- arXiv cs.AIagentsWhat Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon Agents
arXiv:2610.06406v1 Announce Type: new Abstract: As agents take on long-horizon tasks, users shift from making individual decisions to overseeing autonomous execution. Yet the volume of agent activity and the fragmentatio…
- arXiv cs.AIagentsFrom Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?
arXiv:2610.06411v2 Announce Type: replace Abstract: Agentic systems increasingly coordinate molecular-design tools, but it is unclear which layer of the stack limits outcomes on real projects. We developed MAGI, an open…
- arXiv cs.AIagentsAgentPrivArena: Evaluating and Auditing Real-world AI Agent Privacy
arXiv:2610.06454v1 Announce Type: new Abstract: The rapid advancement of LLM agents has enabled systems to autonomously perform complex tasks through external tools, but their growing access to personal data introduces s…
- arXiv cs.AIagentsANT: A Multi-Granularity Network Traffic Dataset and Benchmark for Agents Behavior Auditing
arXiv:2610.06514v1 Announce Type: new Abstract: The growing adoption of large language model (LLM) agents creates a need for network administrators and security teams to audit agent behavior within organizational network…
- arXiv cs.AIagentsHERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention
arXiv:2610.06563v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly capable of acting in complex tool-use environments, yet they often fail to recognize when tasks are infeasible and no val…
- arXiv cs.AIagentsCan Agent Harnesses and Inference Engines Hear Each Other? The HEAR Protocol for Agentic LLM Serving
arXiv:2610.06597v1 Announce Type: new Abstract: LLM agents increasingly execute complex workflows involving multi-turn reasoning, tool use, and parallel agents. Efficient serving requires decisions that span two layers w…
- arXiv cs.AIagentsFREA: A Multi-Source Expert Benchmark for Reaction Feasibility Verification
arXiv:2610.06614v1 Announce Type: new Abstract: As generative models and AI agents propose chemical reactions at a scale beyond expert review, feasibility verifiers decide which proposals enter synthesis planning. But do…
- arXiv cs.AIagentsBack to the Future: Rethinking EDA Infrastructure for Agentic Systems in Chip Design Verification
arXiv:2610.06790v2 Announce Type: replace Abstract: The unprecedented computational scale of modern artificial intelligence depends on complex, multi-billion-transistor Systems-on-Chip, yet the workflows that verify thes…
- arXiv cs.AIagentsOrchestrating Specialized Agents for Trustworthy Enterprise RAG
arXiv:2601.18267v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) shows promise for enterprise knowledge work, yet it often underperforms in high-stakes decision settings that require deep synthesis,…
- arXiv cs.AIagentsAI Agent Pull Requests on GitHub: Frequency, Structure, and Merge Conflict Rates
arXiv:2607.04697v2 Announce Type: cross Abstract: AI coding agents may generate and submit Pull Requests (PRs) to the same repository at the same time. However, research concerning the extent of concurrent submission by…
- arXiv cs.AIagentsUsing Process Mining to Generate AI Agents from Software Engineering Process Records
arXiv:2607.04948v1 Announce Type: cross Abstract: Integrating AI agents into Software Engineering (SE) raises an important challenge: how can we specify and realize AI agents that work effectively alongside humans in hyb…
- arXiv cs.AIagentsOceanMind: A multi-agent AI system for ocean diagnosis
arXiv:2610.03780v1 Announce Type: cross Abstract: Time-dependent, three-dimensional (3D) oceanic multi-variables define coherent states of the evolving ocean to facilitate ocean diagnosis and advance ocean science to bet…
- arXiv cs.AIagentsProsaBuddy: Assisting Mechanized Real-Time Schedulability Analysis with LLM-based Agents
arXiv:2610.03796v1 Announce Type: cross Abstract: Rigorous schedulability analysis is essential for the design of hard real-time systems, yet errors in pen-and-paper proofs threaten the safety of critical applications. T…
- arXiv cs.AIagentsFrom Requirements to Attack Trees: Grounded LLM Agents for Design-Time Security Review
arXiv:2610.03820v1 Announce Type: cross Abstract: Design-level security weaknesses can arise from requirements, trust assumptions, missing controls, and data flows before implementation begins. Existing security practice…
- arXiv cs.AIagentsA study on human-agent teaming through spoken interaction: the impact of human individual traits and agent characteristics
arXiv:2610.04079v1 Announce Type: cross Abstract: Human-agent teams are collaborative systems where humans and agents work interdependently to achieve shared goals. The success of such teams is associated with the human'…
- arXiv cs.AIagentsDependable AI-Assisted Engineering: A Formal Framework for AI Participation and Assurance in Safety-Critical Workflows
arXiv:2610.04084v1 Announce Type: cross Abstract: Generative AI can produce engineering artefacts, but generation alone does not determine whether or how those artefacts should enter safety-critical workflows. This paper…
- arXiv cs.AIagentsDUET: Co-Evolving Solver and Grader Agents
arXiv:2610.04087v1 Announce Type: cross Abstract: Agentic workflows are increasingly used across domains such as technology, finance, and enterprise operations. As these agents become more widely deployed, continually im…
- arXiv cs.AIagentsAgent Reliability Profiles in Financial Services
arXiv:2610.04123v1 Announce Type: cross Abstract: AI agents can take actions. At times, those actions can go beyond what is intended. Agent reliability can be defined as assurance that an agent will stay within intended…
- arXiv cs.AIagentsPB-GRPO: Learning Socially Adaptive LLM Agents from Persona-Driven Simulation with Preference-Batched GRPO
arXiv:2610.04132v1 Announce Type: cross Abstract: Building LLMs that behave well socially, not merely correctly, requires Building LLMs that behave well socially, not merely correctly, requires more than producing locall…
- arXiv cs.AIagentsAgentic Resource Allocation for Batch Multi-Objective Bayesian Optimization in Autonomous Materials Discovery
arXiv:2610.04134v1 Announce Type: cross Abstract: The discovery and development of advanced materials is a challenging process constrained by the high time and monetary costs of synthesis, processing, and characterizatio…
- arXiv cs.AIagentsTrajectory-Derived Confidence for Reliable, Resource-Aware Clinical Text-to-SQL Agents
arXiv:2610.04156v1 Announce Type: cross Abstract: LLM agents for clinical text-to-SQL applications reason autonomously over multiple steps but cannot assess whether their own reasoning or outputs can be trusted. In high…
- arXiv cs.AIagentsAdaptive Operator Selection in Bilevel Large Neighborhood Search for Electric Autonomous Dial-a-Ride Problem under Uncertainty
arXiv:2610.04219v1 Announce Type: cross Abstract: The electric autonomous dial-a-ride problem (EADARP) extends the classical dial-a-ride problem by incorporating battery and charging constraints for electric vehicles. In…
- arXiv cs.AIagentsBenchmarking Psychological Dynamics in Generative Agents
arXiv:2610.04246v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed to simulate human behavior, acting as computational replicas of human subjects. Yet the lived psychological experie…
- arXiv cs.AIagentsPlaying social deduction games with reinforcement fine-tuned large language models
arXiv:2610.04261v1 Announce Type: cross Abstract: Reinforcement fine-tuning (RFT) is increasingly used in applications where large language models (LLMs) interact with humans and other agents. Here we use social deductio…
- arXiv cs.AIagentsHuman Behavior-Informed Crash Scenario Generation with Real-World Crash Priors for Autonomous Vehicle Safety Evaluation
arXiv:2610.04366v1 Announce Type: cross Abstract: Reliable safety evaluation of autonomous vehicles (AVs) is essential to improving road safety, yet it depends critically on realistic simulation of rare crashes. Existing…
- arXiv cs.AIagentsCOPEX: Benchmarking LLM Robustness to Adversarial Context Across Model Context Protocol (MCP) Layers
arXiv:2610.04378v2 Announce Type: replace-cross Abstract: Large language models increasingly mediate tool use in Model Context Protocol (MCP) systems, where adversarial influence may enter through user instructions, tool…
- arXiv cs.AIagentsUnderstanding and Mitigating Hallucination Escape in Tool-Using LLM Agents
arXiv:2610.04409v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly serve as autonomous agents that invoke external tools. However, this capability introduces tool hallucination, selecting incorre…
- arXiv cs.AIagentsMaximizing $p$-Mean Social Welfare in the High-Multiplicity Setting: Few Agent Types and Few Item Types
arXiv:2610.04417v1 Announce Type: cross Abstract: The $p$-mean welfare objective unifies several classical social welfare criteria for the allocation of indivisible goods. We study its maximization under additive nonnega…
- arXiv cs.AIagentsVideo2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos
arXiv:2610.04432v3 Announce Type: replace-cross Abstract: Building interactive simulators from real-world observations is a promising way to scale embodied data, but current pipelines still rely heavily on manual environ…