AI news archive.
4,962 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsGUI-JEPA: Candidate-Conditioned JEPA Latents as a Fast Action Policy for Mobile GUI Agents
arXiv:2610.36877v1 Announce Type: new Abstract: Mobile GUI agents are typically fine-tuned 7B-scale vision-language models (VLMs) that generate each action as text. However, these VLMs decode every action token by token,…
- arXiv cs.AIagentsRubricAtlas: Mining Type-Level Rubrics from Expert Reports to Evaluate Deep Research Agents
arXiv:2610.36878v1 Announce Type: new Abstract: Deep research agents conduct multi-step Web searches and synthesise retrieved information into analytical reports. Evaluating these outputs requires checking which analyses…
- arXiv cs.AIagentsVision-Language Agents Can Learn in Their Own Latent Worlds
arXiv:2610.36925v1 Announce Type: new Abstract: Learning from experience is essential for building the next generation of agents that continually expand their capabilities. Pretrained vision-language models (VLMs) alread…
- arXiv cs.AIagentsProactive Memory for Event-Driven LLM Agents
arXiv:2610.36967v1 Announce Type: new Abstract: Proactive LLM agents anticipate service opportunities from ongoing observations and accumulated history. Existing approaches emphasize recent context or retrieval of relate…
- arXiv cs.AIagentsAutoVend: Benchmarking LLM Agents on Long-Horizon Autonomous Vending Operations
arXiv:2610.36980v1 Announce Type: new Abstract: Large language model (LLM) agents are extending agent-mediated commerce on the Web from shopping for consumers to operating businesses for sellers. In online-to-offline (O2…
- arXiv cs.AIagentsOpenGray: a benchmark for evaluating the decisions of radiotherapy planning agents
arXiv:2610.37081v1 Announce Type: new Abstract: Background and purpose: Radiotherapy planning agents based on large language models (LLMs) decide when to submit a plan or request review but are evaluated mainly by dose.…
- arXiv cs.AIagentsWorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training
arXiv:2610.37161v1 Announce Type: new Abstract: Scaling supervised training for working agents requires diverse professional tasks that yield reliable expert demonstrations. However, missing or inconsistent task informat…
- arXiv cs.AIagentsLiveSearch: Questions as Executable Verifier Code for a Live Benchmark of Professional-Source Financial Search Agents
arXiv:2610.37166v1 Announce Type: new Abstract: In finance, the answer that matters is usually the current one: prices, rates, and disclosures hold only as of a given day, so retrieving up-to-date facts is a core capabil…
- arXiv cs.AIagentsDoes Your Generalist Skill Optimizer Really Incentivize Agentic Tasks? Rethinking Skill Optimization via Bipartite Attribution
arXiv:2610.37201v1 Announce Type: new Abstract: Skill optimizers adapt an agent to long-horizon tasks, such as repairing a terminal environment, by rewriting its skill, a natural-language procedure in its context, and ke…
- arXiv cs.AIagentsGrounding LLM Agents in Business Processes: Process-Aware Knowledge Graphs for Reliable Multi-Step Service Invocation
arXiv:2610.37242v1 Announce Type: new Abstract: Large language model (LLM) agents that call enterprise APIs must select the correct endpoints, follow process order, use valid payload keys, and choose coded values from pr…
- arXiv cs.AIagentsAligning Institutional Power and Operational Ability
arXiv:2610.37342v1 Announce Type: new Abstract: To be socially sustainable, Agentic AI systems require normative designs that align responsibilities with the ability to fulfil them. Identifying incongruences such as unsa…
- arXiv cs.AIagentsAgent-Conditioned Routing: Diverse Reasoning Paths Within One Frozen Model
arXiv:2610.37375v1 Announce Type: new Abstract: Generating several solutions can expose alternative methods, but additional trajectories often paraphrase one dominant approach. We investigate whether the conditional capa…
- arXiv cs.AIagentsClearing the FoG: Training KG Agents to Retrieve the Evidence Behind Their Answers
arXiv:2610.37405v1 Announce Type: new Abstract: Large language models (LLMs) can answer many factual questions correctly, but a correct answer is not necessarily a supported one. For an LLM agent, a knowledge graph (KG)…
- arXiv cs.AIagentsConstraining the Commit Boundary: A DIO/ODI-Informed Authorization Guardrail for Agentic Entity Resolution
arXiv:2610.37407v1 Announce Type: new Abstract: Agentic Entity Resolution (ER) systems iteratively plan actions, retrieve evidence, revise hypotheses, and propose graph mutations. An erroneous identity hypothesis may con…
- arXiv cs.AIagentsM4Bench: Evaluating Procedural Specification for Clinical EHR Derivation Agents
arXiv:2610.37459v1 Announce Type: new Abstract: Clinical research over electronic health records depends on derived variables whose definitions sit outside the schema, in item codes, time windows, missingness rules, and…
- arXiv cs.AIagentsConcordat: Typed Sessions for LLM Agents
arXiv:2610.37461v2 Announce Type: replace Abstract: Agents built on large language models are increasingly allowed to take consequential actions: cancelling bookings, issuing refunds, changing accounts. The rules that go…
- arXiv cs.AIagentsFrom Interaction to Capability: Task Advancement as State and Supervision for GUI Agents
arXiv:2610.37482v1 Announce Type: new Abstract: GUI memory should preserve the results of past actions and learn reusable operations. This is difficult in long-horizon workflows, where agents must use information across…
- arXiv cs.AIagentsTeamGym: A Gym for Team Decision-Making by AI Agents with Distributed Information
arXiv:2610.37571v1 Announce Type: new Abstract: Many real-world decisions require teams to integrate information distributed across participants. Yet AI agents are still primarily trained and benchmarked in isolation. We…
- arXiv cs.AIagentsSCOPE: Source Credibility and Outlet Profiling Engine
arXiv:2610.35929v1 Announce Type: cross Abstract: We present SCOPE, a multi-agent system for profiling news media outlets with respect to bias, factuality, and credibility. Given an outlet URL, SCOPE coordinates speciali…
- arXiv cs.AIagentsWho Convinced Whom? Tracing How LLMs Change Their Minds in Multi-Agent Systems
arXiv:2610.35930v1 Announce Type: cross Abstract: Multi-agent debate (MAD) aims to improve language-model decisions through the exchange of arguments, yet agreement after debate need not reflect independent corroboration…
- arXiv cs.AIagentsCurriculum-Driven Deep Reinforcement Learning for Autonomous Far-Range Rocket Landing
arXiv:2610.35954v1 Announce Type: cross Abstract: Autonomous vertical landing of reusable launch vehicles is a critical yet formidable challenge in aerospace engineering, primarily due to highly nonlinear dynamics, strin…
- arXiv cs.AIagentsAgentBaton: Efficient Model Collaboration in Agentic Tasks
arXiv:2610.35959v1 Announce Type: cross Abstract: Solving long-horizon agentic tasks requires language agents to interact with their environments over multiple steps, and reliable performance often comes from the expensi…
- arXiv cs.AIagentsA Hyper-Logical View on Multi-Agent Path Planning
arXiv:2610.35964v1 Announce Type: cross Abstract: Multi-Agent Path Planning (MAPP) requires collision-free paths for multiple agents. MAPP has numerous real-life applications, including the navigation of automated vehicl…
- arXiv cs.AIagentsEMMA: Structured Episodic Memory for Multi-Agent Workflow Synthesis
arXiv:2610.35966v1 Announce Type: cross Abstract: Deploying LLM agents in specialized domains often require fine-grained task-specific procedures and knowledge a general model lacks, yet parameter training is costly and…
- arXiv cs.AIagentsUnityBench-Mini3D: Evaluating LLM Agents for 3D Game Development in Unity
arXiv:2610.35980v1 Announce Type: cross Abstract: Game development stresses coding agents in ways general software engineering does not: correctness depends on how engine APIs, serialized scene state, and runtime behavio…
- arXiv cs.AIagentsGeneration and Verification: Human-Agent Collaboration for Safety-Critical Automotive Software Engineering
arXiv:2610.35982v1 Announce Type: cross Abstract: Research on coding agents mainly focuses on generation quality. Yet, safety-critical automotive software makes two additional demands. It prioritizes verification, since…
- arXiv cs.AIagentsPROBE: Frontier Coding Agents Find Different Bugs Than Maintainers Fix
arXiv:2610.35987v1 Announce Type: cross Abstract: Proactive bug discovery is an important software-engineering problem. Even though coding agents are already widely deployed in this domain, their capabilities remain unde…
- arXiv cs.AIagentsPolicyMediator: Multi-Regional Policy Learning through Mediation Agents with Evolving Skills in OPC Ecosystems
arXiv:2610.35997v1 Announce Type: cross Abstract: One-person companies (OPCs) are emerging enterprises operated by individual entrepreneurs through digital platforms and LLM-based AI agents. These highly skilled entrepre…
- arXiv cs.AIagentsCIVER: Causal Intervention Verification for Reliable Code Review
arXiv:2610.36010v1 Announce Type: cross Abstract: Code review is essential for maintaining software repositories by identifying defects, improving code quality, and supporting reliable software evolution. With the growin…
- arXiv cs.AIagentsDo Coding Agents Still Need a Debugger? Frontier-Model-Based Fault Localization at the Accuracy Ceiling
arXiv:2610.36015v1 Announce Type: cross Abstract: Background: To localize a fault, a coding agent can reason from source code alone or use debugger assistance by running the program and stepping through it in an interact…
- arXiv cs.AIagentsLog-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol
arXiv:2610.36108v1 Announce Type: cross Abstract: LLM agents increasingly access external tools through the Model Context Protocol (MCP), but the natural-language metadata used to describe those tools creates a prompt-in…
- arXiv cs.AIagentsContext Is a Pipeline, Not a Window: Information Attrition in LLM Agent Harnesses
arXiv:2610.36114v1 Announce Type: cross Abstract: LLM agents are judged by two numbers: the size of the context window, and how often the final answer is correct. Both numbers miss a third thing: how much of a tool's out…
- arXiv cs.AIagentsWhen Connectivity Misleads: Guiding Agentic Search with Contrastive Evidence Paths
arXiv:2610.36134v1 Announce Type: cross Abstract: Search agents can use cross-document graphs to discover sources through multi-hop connections and choose subsequent actions based on candidate rankings and relationships…
- arXiv cs.AIagentsReplication or Corroboration? An Axiomatic Framework for Evidential Dependence in Multi-Agent Debate
arXiv:2610.36151v1 Announce Type: cross Abstract: In multi-agent debates, matching reports can arise for two different reasons: agents may repeat the same evidence (replication), or they may provide separate evidential r…
- arXiv cs.AIagentsStratum: Repository Memory for Coding Agents Beyond the Context Window
arXiv:2610.36153v1 Announce Type: cross Abstract: Context windows have grown a thousand-fold, yet coding agents still start every session with no memory of their past work. They re-read files, retry failed approaches, an…
- arXiv cs.AIagentsCan AI Guide Testing Without Generating Tests? A Comparative Study of AI-Assisted Unit Testing
arXiv:2610.36185v1 Announce Type: cross Abstract: Recent advances in generative AI have enabled assistants to generate increasingly sophisticated executable unit tests. However, novices may accept these outputs without i…
- arXiv cs.AIagentsAgent or Human? Detecting Commits by AI Coding Agents in the Absence of Authorship Signatures
arXiv:2610.36229v1 Announce Type: cross Abstract: AI coding agents such as Claude Code, GitHub Copilot coding agent, and Cursor now commit directly to open-source repositories. Empirical studies of these agents identify…
- arXiv cs.AIagentsBUSTA: Teaching Small Language Models to Reason About Binary Execution
arXiv:2610.36288v1 Announce Type: cross Abstract: Large Language Models (LLM) are increasingly applied to Reverse Engineering (RE) workflows. RE, however, differs from common LLM coding tasks as it requires models to rea…
- arXiv cs.AIagentsHIDRA: Hierarchical Dual-Routing Attention for Replay-Free Lifelong Imitation Learning
arXiv:2610.36374v1 Announce Type: cross Abstract: Robotic agents operating in real-world environments must adapt continuously from a stream of multimodal demonstrations, often under constraints that preclude storing or r…
- arXiv cs.AIagentsFIDES-Live: Evaluating Behavioral Concordance in Sequential Trading Agents
arXiv:2610.36476v1 Announce Type: cross Abstract: Sequential trading agents produce decisions, orders, execution receipts, account states, and reports that need not agree, even when the final portfolio value is correctly…
- arXiv cs.AIagentsRoboAuto: Autonomous Robot Program Search through Multi-Level Physical Understanding
arXiv:2610.36533v1 Announce Type: cross Abstract: Recently, LLM-based autonomous agents have shown strong capabilities in iteratively generating, evaluating, and refining executable solutions. In robotic manipulation, Co…
- arXiv cs.AIagentsNextEval: An Agent-Based Solver and Benchmark for Derivative-Free Optimization
arXiv:2610.36553v1 Announce Type: cross Abstract: Derivative-free optimization (DFO) addresses problems where derivatives are unavailable or costly to obtain. This setting often arises in simulation-based and experimenta…
- arXiv cs.AIagentsBenchmarking LLM Agents for Behaviorally Adequate Test Generation from Software Requirements
arXiv:2610.36584v1 Announce Type: cross Abstract: As large language model agents increasingly compile natural-language requirements into repository-level code, requirement-to-test generation grows in importance to provid…
- arXiv cs.AIagentsAtom as an Agent: Emergent Order by Collective Predictive Coding
arXiv:2610.36673v1 Announce Type: cross Abstract: What is the intrinsic reason of emergence of macroscopic order parameter out of microscopic systems? In this article, we apply to physics the collective predictive coding…
- arXiv cs.AIagentsFrom Voiceprints to User Entities: Online Speaker-Memory Construction for Multi-User Spoken Agents
arXiv:2610.36713v1 Announce Type: cross Abstract: Personalized spoken agents must identify speakers before accessing user-specific memory, yet memory benchmarks typically assume correctly attributed histories. We argue t…
- arXiv cs.AIagentsBeyond QASecClaw: Agent Scaling, Verifier Feedback, and Evidence Reliability in Software Assurance
arXiv:2610.36947v1 Announce Type: cross Abstract: Can additional specialist language-model contexts improve software assurance when deterministic tool evidence is already available? We study this question through five ex…
- arXiv cs.AIagentsBlindfold: Keeping the Audit Coin Secret from LLM Agents
arXiv:2610.37055v1 Announce Type: cross Abstract: Audit-based certification bounds the violation rate of an LLM agent by auditing a random fraction $\varepsilon$ of actions and reweighting the audited labels; its validit…
- arXiv cs.AIagentsMLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model
arXiv:2610.37175v1 Announce Type: cross Abstract: AI research agents can propose, execute, and improve programs that solve machine learning tasks. However, executing each candidate program requires training and evaluatin…
- arXiv cs.AIagentsAction-Value Calibration via Continuation Sharing for Long-Horizon Agentic Reinforcement Learning
arXiv:2610.37195v1 Announce Type: cross Abstract: Reinforcement learning for long-horizon agents relies on feedback from sequences of interactions, making credit assignment to individual actions difficult. Existing metho…
- arXiv cs.AIagentsSpine: Compiling Subtask Trees into Structured Context for Long-Horizon Coding Agents
arXiv:2610.37224v1 Announce Type: cross Abstract: Long-horizon coding tasks contain nested subtasks. Typically, agents record interactions sequentially into a growing history, causing context inflation and performance de…