AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsOntoAct: Hypothesis-Based Neuro-Symbolic Agents through Ontological Abstraction
arXiv:2610.21983v1 Announce Type: new Abstract: Learning from experience requires recovering reusable knowledge and determining when it applies to a new situation. We introduce OntoAct, a hypothesis-based neuro-symbolic…
- arXiv cs.AIagentsCARA: Causally Guided Retrieval Agent for Question Answering
arXiv:2610.22017v1 Announce Type: new Abstract: Retrieval-augmented generation over text-rich knowledge graphs requires identifying evidence that contributes to answering a question, rather than merely matching its textu…
- arXiv cs.AIagentsGraphACM: Graph-based Action Consistency Measurement for Uncertainty Quantification in LLM Agents
arXiv:2610.22031v1 Announce Type: new Abstract: Behavioral consistency across repeated executions provides an informative signal for assessing the reliability of large language model (LLM) agents. However, existing appro…
- arXiv cs.AIagentsFAOPs: Normal Forms and an Algebra for AI Agent Workflows
arXiv:2610.22061v1 Announce Type: new Abstract: Organizations increasingly encode operational procedures as multi-step agent skills, here called Agent Operating Procedures (AOPs), that must be traceable, auditable, repro…
- arXiv cs.AIagentsPROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
arXiv:2610.22124v1 Announce Type: new Abstract: Modern agentic systems extend language models with external tools, enabling them to complete complex tasks through multi-turn interactions. As these agents are deployed in…
- arXiv cs.AIagentsBelieved but Not Said: Measuring Hidden Belief Collapse in Multi-Agent LLM Discussions
arXiv:2610.22138v1 Announce Type: new Abstract: LLM systems increasingly rely on groups of agents that discuss, critique, and check one another, assuming that peers will catch individual errors. We test this assumption a…
- arXiv cs.AIagentsRealtime-Bench: Can Frontier Models Solve Real-time Interactive Problems?
arXiv:2610.22155v3 Announce Type: replace Abstract: Real-time interaction requires agents to perceive evolving environments and act under temporal constraints, yet existing evaluations of real-time streaming models focus…
- arXiv cs.AIagentsTerminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine
arXiv:2610.22192v3 Announce Type: replace Abstract: Converting verifier outcomes into useful policy updates and partial progress into complete task resolution is crucial for terminal agents. We present Terminal-RSI, whic…
- arXiv cs.AIagentsAutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning
arXiv:2610.22194v1 Announce Type: new Abstract: Language model agents increasingly automate post-training, but when given the full training stack they converge on supervised fine-tuning and spend most effort revising tra…
- arXiv cs.AIagentsHTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent Orchestration
arXiv:2610.22195v2 Announce Type: replace Abstract: Orchestrating multiple agents on a complex task requires reconciling local subtask execution with global task planning. Dynamic dispatch approaches provide execution fl…
- arXiv cs.AIagentsShortcut Sensitivity in Agent-Safety Evaluations
arXiv:2610.22243v1 Announce Type: new Abstract: AI agents take actions through tools. Some actions are sensitive, so guards that supervise them must themselves be evaluated reliably. Yet the data used to evaluate a guard…
- arXiv cs.AIagentsX-RIC: An Agentic RAN-Intelligent Controller Benchmark for Enhancing Reinforcement Learning
arXiv:2610.22269v1 Announce Type: new Abstract: The O-RAN ALLIANCE introduces architectural flexibility through disaggregation and AI-driven control. While the RAN Intelligent Controller (RIC) enables centralized optimiz…
- arXiv cs.AIagentsLEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents
arXiv:2610.22280v1 Announce Type: new Abstract: Computer-use agents increasingly tackle long-horizon tasks, where running a frontier model at every step is expensive and a small open-weight model alone often fails. Weak-…
- arXiv cs.AIagentsImproving Environment-Agnostic Agents: The Role of Scaffolding
arXiv:2610.22289v3 Announce Type: replace Abstract: Agents built on stronger language models may increasingly construct useful procedures for themselves, reducing the advantage of developer-supplied scaffolding. We inves…
- arXiv cs.AIagentsA team of Gemini 4 Argon agents beats Minecraft
arXiv:2610.22319v1 Announce Type: new Abstract: We placed four Gemini 4 Argon agents in a sandboxed Minecraft survival world and gave them one goal: defeat the Ender Dragon. Each agent controlled a player via an open-sou…
- arXiv cs.AIagentsKnowGPO: Knowledge-Grouped Policy Optimization for Search Agents
arXiv:2610.22331v1 Announce Type: new Abstract: Deep search agents solve knowledge-intensive tasks through long-horizon, multi-turn interactions, where assigning credit to individual search decisions is fundamentally dif…
- arXiv cs.AIagentsMLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering
arXiv:2610.22344v1 Announce Type: new Abstract: Large language models (LLMs) are expanding from assisting scientific research and engineering to autonomously developing and improving AI systems, advancing AI for AI (AI4A…
- arXiv cs.AIagentsFDE-Gym: The Last Mile of AI Delivery
arXiv:2610.22350v1 Announce Type: new Abstract: Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets. Real-world customer delivery is diffe…
- arXiv cs.AIagentsTruth for Believable AI: Expressed Doubt, Provenance, and Belief Revision as an Engineerable Stance
arXiv:2609.26035v1 Announce Type: cross Abstract: Conversational agents often express answers in a uniformly confident register. We test whether expressed uncertainty, provenance-aware assertion, and explicit belief revi…
- arXiv cs.AIagentsRICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting
arXiv:2609.34004v2 Announce Type: cross Abstract: Equity-relevant news evolves through temporally dependent corporate events, making historical information useful only when event continuity, information availability, and…
- arXiv cs.AIagentsINFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems
arXiv:2610.20776v1 Announce Type: cross Abstract: LLM-based agents increasingly execute long-horizon, end-to-end workflows involving shell commands, code modification, dependency installation, and interaction with remote…
- arXiv cs.AIagentsSHRED: Self-Play for Heterogeneous Road-Users without Expert Demonstrations
arXiv:2610.20866v1 Announce Type: cross Abstract: Realistic traffic simulation and autonomous planning both depend on modeling interactions among heterogeneous road users whose dynamics, constraints, and behaviors differ…
- arXiv cs.AIagentsScrewtape: Adversarial Transcript Editing for Monitor Red-Teaming
arXiv:2610.20941v1 Announce Type: cross Abstract: We present Screwtape, a pipeline that converts real agent transcripts into attacks that evade action-only monitors. An LLM attacker edits a transcript so that the agent c…
- arXiv cs.AIagentsSame Context, Different Agents: A Behavioral Study of Semantic Layers, Multi-Agent Orchestration and Memory Compaction in Data Agents
arXiv:2610.20959v2 Announce Type: replace-cross Abstract: Answering questions over heterogeneous data means combining evidence from files, databases, documents and the web. Data agents automate this, but their success de…
- arXiv cs.AIagentsSCARCE: Emergent Institutions in Long-Horizon Multi-Agent Coding Systems
arXiv:2610.21029v2 Announce Type: replace-cross Abstract: As autonomous agents become widely deployed, coordinating access to shared computing resources and services will become increasingly important. Recent incidents h…
- arXiv cs.AIagentsReviewPilot: A Multi-Agent System for Screening and Data Extraction in Systematic Reviews
arXiv:2610.21042v1 Announce Type: cross Abstract: Systematic literature reviews follow the PRISMA process of screening scholarly works and extracting evidence from included studies. Deep research tools based on large lan…
- arXiv cs.AIagentsApprove What, Exactly? Effect Binding and Trusted Rendering for Agent Step-Up Authorization
arXiv:2610.21063v1 Announce Type: cross Abstract: AI agents now pause for approval before they send money, delete files or email outsiders, and that approval is usually treated as a second factor. We argue it is one only…
- arXiv cs.AIagentsToolBottleneckBench: Measuring Tool-Agent Performance under Controlled Pressures and Fixed Harness Budgets
arXiv:2610.21098v1 Announce Type: cross Abstract: The success score of a tool agent reflects both its model and the budgets of the harness that runs it. We present ToolBottleneckBench, a benchmark that measures tool-agen…
- arXiv cs.AIagentsSSR: Structural Signal Retriever for Scalable Agent Discovery in LLM-Orchestrated Multi-Agent Systems
arXiv:2610.21113v1 Announce Type: cross Abstract: Large-scale multi-agent ecosystems require mechanisms for discovering suitable agents without exposing entire registries to a large language model (LLM) orchestrator. The…
- arXiv cs.AIagentsStronger Judges Do Not See More: Deployment-Integrity Blindness in LLM Evaluation
arXiv:2610.21135v1 Announce Type: cross Abstract: LLM-agent evaluation reports behavioral scores but leaves the identity of the deployed runtime stack unreported. A tampered deployment that preserves evaluated outputs pa…
- arXiv cs.AIagentsA Responsibility-Centered Coordination Mechanism for Decentralized Multi-Agent Systems
arXiv:2610.21243v1 Announce Type: cross Abstract: Centralized orchestration provides comprehensive multi-agent coordination but creates bottlenecks in scalability, adaptability, and collective performance. Decentralized…
- arXiv cs.AIagentsTRACER: Trajectory-Aware Tool Retrieval for LLM Agents
arXiv:2610.21267v1 Announce Type: cross Abstract: Modern agents select tools from registries, but exposing entire registries incurs high token costs and can impair selection as they grow. We present TRACER, a retrieval f…
- arXiv cs.AIagentsMemorilla: Latent Semantic Memory for LLMs
arXiv:2610.21375v2 Announce Type: replace-cross Abstract: Memory enables large language models (LLMs) to use information beyond their parameters, such as past user conversations, long documents, or an agent's earlier act…
- arXiv cs.AIagentsPriorityFEC: Deadline-Aware Streaming FEC for KV-Cache Handoff in Edge Multi-Agent Systems
arXiv:2610.21390v2 Announce Type: replace-cross Abstract: Multi-agent large language model (LLM) systems are increasingly deployed at the edge to support complex tasks that require collaboration and information exchange…
- arXiv cs.AIagentsMatoi: Selective Revalidation of Consequence Evidence for Agent Authorization
arXiv:2610.21394v1 Announce Type: cross Abstract: Matoi separates reusable consequence evidence from current execution authority and durable occurrence history. Its finite query-aware contract covers branches, ordered co…
- arXiv cs.AIagentsX-Fly: Learning to Reach and Stop in Full-Chunk Aerial Vision-Language Navigation
arXiv:2610.21450v1 Announce Type: cross Abstract: Aerial vision-language navigation (VLN) agents built on large vision-language models are expensive to query. Executing a complete predicted action chunk before replanning…
- arXiv cs.AIagentsTrajectory-Level Speculation with Semantic Verification for Tool-Using Agents
arXiv:2610.21463v1 Announce Type: cross Abstract: Large language model agents solve tasks through long sequences of tool calls, and the prevailing design has a single strong model generate every step, although many steps…
- arXiv cs.AIagentsPoison Valleys: Diagnosing Path-Dependent Failure in LLM Code Repair
arXiv:2610.21514v1 Announce Type: cross Abstract: When code-repair agents fail, final tests reveal that a patch is wrong but not which earlier commitment caused it or which software obligation failed. Poison Valleys trac…
- arXiv cs.AIagentsDialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents
arXiv:2610.21561v5 Announce Type: replace-cross Abstract: Large language models (LLMs) deployed as conversational agents are increasingly expected to follow procedural logic. While factual hallucination has received exte…
- arXiv cs.AIagentsIndependent Data-Integrity Verification for LLM-Driven Functional Coverage Closure in Hardware Design
arXiv:2610.21570v1 Announce Type: cross Abstract: LLM agents can write directed tests that close functional coverage, but coverage only shows that a state was reached, not that the data on the way there was correct. This…
- arXiv cs.AIagentsRethinking the Role of Tool Graph Memory in Multi-Turn Tool Use
arXiv:2610.21571v1 Announce Type: cross Abstract: Large language model (LLM) agents solve complex tasks by calling external tools over multiple turns. Recent work has proposed tool graph memory, which stores past experie…
- arXiv cs.AIagentsHuman Interventions as Labels: Localizing, Steering, and (Sometimes) Editing the Computations Behind LLM Agent Failures
arXiv:2610.21708v1 Announce Type: cross Abstract: When an LLM agent misbehaves, a human steps in, and that intervention is usually discarded or replayed as training data. We treat it instead as a measurement: a label poi…
- arXiv cs.AIagentsReliable Knowledge Acquisition for Continual Learning Agents
arXiv:2610.21739v1 Announce Type: cross Abstract: As agents powered by foundation models move into open-ended environments, continual learning from experience becomes essential. For agents built on models with fixed para…
- arXiv cs.AIagentsThe Delegation Dilemma: Economies of Scale, Accountability, and Polycentric Governance
arXiv:2610.21746v1 Announce Type: cross Abstract: Many collective-action systems are neither fully decentralized nor fully centralized: agents voluntarily organize into institutions that share organizational costs and de…
- arXiv cs.AIagentsLearning Rewards in Strategic Games
arXiv:2610.21912v1 Announce Type: cross Abstract: Understanding the objectives that drive agents' behavior is crucial in strategic environments, where multiple agents interact and adapt to one another. This challenge ari…
- arXiv cs.AIagentsCodeHealth Predicts the Token Cost of Agentic Code Review: A Pre-Registered Study of 465 Agent-Authored Pull Requests
arXiv:2610.21914v1 Announce Type: cross Abstract: Context: Organizations increasingly delegate code review to multi-agent large language model (LLM) pipelines billed per token. Low code quality raises human maintenance e…
- arXiv cs.AIagentsAgentic-Priors: Using Large Language Models to Address the Cold Start Problem in Preference Elicitation
arXiv:2610.21938v1 Announce Type: cross Abstract: An agent that learns a user's preferences from their choices faces a cold start problem: before any choices are observed, it must rely solely on a prior. Informative prio…
- arXiv cs.AIagentsPriming Base Models for Agentic Post-Training: An Open Midtraining Recipe
arXiv:2610.22019v1 Announce Type: cross Abstract: Frontier models, general-purpose and domain-specific alike, now include a midtraining stage between pretraining and post-training, but little has been published about how…
- arXiv cs.AIagentsSelection Is Not Learning: Choosing Model Futures
arXiv:2610.22029v1 Announce Type: cross Abstract: Self-evolving language models train on tasks they generate, so every round must decide which updated model the next round inherits. Current loops such as R-Zero, Agent0,…
- arXiv cs.AIagentsSpecification Gaming and a Constrained Reinforcement Learning Mitigation in a Cleaning Gridworld
arXiv:2610.22152v1 Announce Type: cross Abstract: Reinforcement learning agents optimize exactly the reward signal they are given, which can diverge sharply from an intended true objective when that signal is only a prox…