AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsWhen Skills Remain But Access Fails: Factorized Skill Memory for Continual Skill Internalization
arXiv:2610.15492v1 Announce Type: new Abstract: Skill internalization aims to convert externally specified procedural skills into persistent model capabilities, allowing language-model agents to execute them without retr…
- arXiv cs.AIagentsAgent-Canary-Mas: End-to-End Evaluation of Protocol Risk in Long-Horizon Multi-Agent Systems
arXiv:2610.15529v2 Announce Type: replace Abstract: Agent-to-agent protocols allow LLM agents to discover peers, exchange results, and coordinate tool use. A locally successful protocol attack, however, may be rejected b…
- arXiv cs.AIagentsInverse Garment Design with Visual Agents
arXiv:2610.15582v1 Announce Type: new Abstract: We study the problem of inverse garment design, reconstructing simulation-ready 3D outfits with arbitrary layers from a single image, with visual agents. Unlike differentia…
- arXiv cs.AIagentsRecall What Is Missing: Composing Evidence from Long-Term Agent Memory
arXiv:2610.15642v1 Announce Type: new Abstract: Under a limited context budget, a long-term agent must recall not merely memories that are individually relevant, but evidence that is collectively sufficient for the curre…
- arXiv cs.AIagentsSpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications
arXiv:2610.15708v1 Announce Type: new Abstract: Coding agents based on frozen language models can improve their performance by refining the external context they rely on, without updating model weights. We study recursiv…
- arXiv cs.AIagentsSuggested Is Not Superseded: A Pre-Registered Evaluation of a System-One Model as a Memory-Retirement Gate
arXiv:2610.15710v1 Announce Type: new Abstract: Long-term memory for assistants needs a gate that decides when a new utterance retires an old stored claim. Benchmark labels for this step mark a pair as changed or not, so…
- arXiv cs.AIagentsMedHarnessBench: A Unified Benchmark for Healthcare Agent Evaluation
arXiv:2610.15714v1 Announce Type: new Abstract: Healthcare agents must transform longitudinal clinical evidence into reliable actions through heterogeneous tools and stateful workflows, conditions under which model-centr…
- arXiv cs.AIagentsGoogle Earth AI Geospatial Reasoning Agent: Capabilities and a Systematic Evaluation
arXiv:2610.15750v1 Announce Type: new Abstract: Google Earth AI is a family of geospatial AI models, together with an agent that orchestrates them. We present this agent, Google Earth AI's Geospatial Reasoning agent (GRA…
- arXiv cs.AIagentsAgent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams
arXiv:2610.15788v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly deployed as teams, yet they fail in characteristically social ways: information holders stay silent, dominant speakers an…
- arXiv cs.AIagentsRetryBench: Separating Retry Permission from Recovery Outcomes in GPT Tool Use
arXiv:2610.15884v3 Announce Type: replace Abstract: False retry permission (FRP) occurs when an agent retries a timed-out tool call without support from the visible contract. RetryBench separates this error from realized…
- arXiv cs.AIagentsVision: "What Don't I Know About User's Preferences?" How Uncertainty Estimation Improves Proactive Assistant Alignment
arXiv:2610.15948v1 Announce Type: new Abstract: Proactive Smart Assistants (PSAs) increasingly use general knowledge, learned patterns from group-level data, patterns from individual user's data, and recent sensor observ…
- arXiv cs.AIagentsSmall but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents
arXiv:2610.15964v1 Announce Type: new Abstract: A self-evolving agent rewrites its own harness and must decide which rewrites to keep, so its improvement signal is the check a rewrite has to pass. Verifying a rewrite by…
- arXiv cs.AIagentsPopGen: Generating Semantically Diverse Populations for Zero-Shot Coordination
arXiv:2610.15969v1 Announce Type: new Abstract: In multi-agent reinforcement learning, exposing a cooperator to partners with diverse strategies during training is key to better collaboration at test time. However, exist…
- arXiv cs.AIagentsRevocation Is Not Complete at Receipt: An Executable Outcome Contract for Distributed Agent-Tool Gateways
arXiv:2610.15991v1 Announce Type: new Abstract: Distributed agent workflows cache delegated authority at tool gateways. Revocation may be reported at issuer commit, transport acknowledgment, or receiver persistence, alth…
- arXiv cs.AIagentsComputational Reflective Equilibrium for Agentic AI: A Rawlsian Alignment Scaffold for Governance
arXiv:2610.16015v1 Announce Type: new Abstract: The rapid deployment of agentic AI has introduced complex challenges for the ethics and governance of AI systems. Agents built on large language models act through tools on…
- arXiv cs.AIagentsUnderstanding and Reducing Misalignment in Persuasion Optimization
arXiv:2610.16070v1 Announce Type: new Abstract: Frontier models are now trained for complex multi-agent tasks, from running a company to engaging in negotiations. These tasks necessitate training models to be persuasive.…
- arXiv cs.AIagentsHeterogeneous Agentic Coevolution
arXiv:2610.16078v1 Announce Type: new Abstract: Recent advances in self-improving LLM agents have demonstrated the potential of AI systems that drive their own intelligence. However, many domain-specific applications rel…
- arXiv cs.AIagentsBeyond Perfect Teammates: Multi-Agent Collaboration with Unreliable Colleagues
arXiv:2610.16117v2 Announce Type: replace Abstract: LLM-based multi-agent collaboration is increasingly used to solve complex tasks by dividing work among specialized agents and integrating complementary expertise. Yet e…
- arXiv cs.AIagentsImitation Holds a Key to Evolution: Localized Repair and Verified Skill Acquisition for Adaptive Agents
arXiv:2610.16125v1 Announce Type: new Abstract: An agent can retain successful trajectories without learning which part of an experience should repair a new discrepancy. We formulate passive imitation (PI) as an architec…
- arXiv cs.AIagentsPhantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another
arXiv:2610.16141v1 Announce Type: new Abstract: LLM agents increasingly operate over multiple entities, where reliable response generation requires not only retrieving relevant evidence but also preserving its associatio…
- arXiv cs.AIagentsPollard: Governed Semantic Execution Trees for Framework-Independent AI Agent Control and Replay
arXiv:2610.16145v1 Announce Type: new Abstract: Agent frameworks can persist checkpoints, trace tool calls, and limit resource use, but these facilities often assign different identities to execution, governance, and rep…
- arXiv cs.AIagentsUncovering Robustness Weaknesses in LLM Agents via Persona Evolution with Task-Integrity Constraints
arXiv:2610.16155v1 Announce Type: new Abstract: Interactive-agent evaluations commonly rely on standardized LLM-based user simulators that exhibit broadly cooperative behavior, potentially overlooking failures that arise…
- arXiv cs.AIagentsLearning to GUIDE the Group: Self-Learning LLM Facilitation Across Multi-Party Tasks
arXiv:2610.16231v1 Announce Type: new Abstract: As large language models are increasingly adopted as multi-party communication facilitators, there is a growing demand for agents capable of balancing diverse group dynamic…
- arXiv cs.AIagentsagent-risk: Risk Assessment for Changes to AI Agents
arXiv:2610.16280v1 Announce Type: new Abstract: Before changing a deployed AI agent (a stricter safety gate, a new model), organizations must approve the change, starting from existing logs. Extending classical risk anal…
- arXiv cs.AIagentsREVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces
arXiv:2610.16288v2 Announce Type: replace Abstract: Frontier LLM agents perform complex interactive tasks, but their inference costs motivate transferring their experience to smaller open-source agents. Distillation and…
- arXiv cs.AIagentsReTAC: Residual Test-Time Agentic Computation for Video Spatial Reasoning
arXiv:2610.16315v1 Announce Type: new Abstract: Test-time agentic computation can improve multimodal large language models (MLLMs) through planning, tool use, iterative perception, and reflection, but indiscriminate comp…
- arXiv cs.AIagentsHyWe: Unifying Search and Operation for Real-World Hybrid Web Tasks
arXiv:2610.16319v2 Announce Type: replace Abstract: Real-world hybrid web tasks need both information gathering and page interaction, yet search-based and operation-based agents are developed and evaluated separately. To…
- arXiv cs.AIagentsTRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents
arXiv:2610.16333v1 Announce Type: new Abstract: As AI agents increasingly act through external tools, tool results are no longer simple outputs but execution artifacts that must remain correctly associated with the conte…
- arXiv cs.AIagentsEfficient Multi-Agent Reasoning via Confidence-Guided Adaptive Debate
arXiv:2610.16343v1 Announce Type: new Abstract: Multi-agent debate has shown promise for improving the reasoning of large language models, yet recent theory suggests its benefits are highly regime-dependent. While intera…
- arXiv cs.AIagentsRecursive Environment Scaling for General Long-Horizon Agents
arXiv:2610.16397v2 Announce Type: replace Abstract: We study environment scaling as a way to increase agent-benchmark difficulty while holding core task objectives fixed. Our framework, Recursive Environment Scaling (RES…
- arXiv cs.AIagentsEvoWeb: A Benchmark for Coding Agents on Evolving Web Applications
arXiv:2610.16402v1 Announce Type: new Abstract: Web application development often proceeds through successive requests that extend an existing implementation. Yet web-generation benchmarks primarily evaluate development…
- arXiv cs.AIagentsSLS-Bench: A Benchmark for Incident Log Summarization with Synthetic Observability Data
arXiv:2610.16412v1 Announce Type: new Abstract: As IT systems grow in complexity, automated agent-driven incident response becomes increasingly critical. A key capability for these agents is summarizing large log streams…
- arXiv cs.AIagentsAuthGateBench: Benchmarking LLMs as Authorization Gate
arXiv:2610.16426v1 Announce Type: new Abstract: Automated approval systems let coding agents execute high-risk actions with minimal human oversight by delegating the authorization decision to a classifier, typically a la…
- arXiv cs.AIagentsXAI-Guided Fourier Domain Generalisation for Pure-Simulation Sim-to-Real Deep Reinforcement Learning
arXiv:2610.16478v1 Announce Type: new Abstract: Deep reinforcement learning has shown strong potential for vision-based autonomous driving, but policies trained in simulation often suffer severe performance degradation w…
- arXiv cs.AIagentsEAU: Environment-Agent-User Co-evolution for Training User-Centric Agents
arXiv:2610.16523v1 Announce Type: new Abstract: Training LLM agents to interact with users over multiple turns is challenging because the learning signal depends not only on the agent, but also on the user simulator and…
- arXiv cs.AIagentsOvertaught, Underlearned: Learner-Centered Distillation from Multi-Agent Discussion
arXiv:2610.16543v1 Announce Type: new Abstract: Multi-agent discussion produces reasoning collaboratively, while deployment still relies on a smaller student that must answer alone. Full-graph distillation transfers such…
- arXiv cs.AIagentsG$^2$WAM: World Action Models for Efficient and Geometry Grounded Image-Goal Navigation
arXiv:2610.16558v1 Announce Type: new Abstract: World models capture environment dynamics and support counterfactual reasoning for planning. In image-goal navigation, where the target often lies beyond the current field…
- arXiv cs.AIagentsStructural Baselines Matter for Agent Failure Detection and Attribution
arXiv:2610.16661v1 Announce Type: new Abstract: An LLM agent using tools can fail silently. It stops before the task is done, raises no error, and answers fluently. Two kinds of monitor address this, one deciding whether…
- arXiv cs.AIagentsTrace-to-Architecture: Capability Bottleneck Diagnosis for Harness Revision
arXiv:2610.16725v1 Announce Type: new Abstract: Improving an LLM agent requires knowing what to change when it fails. Similar failures can require different fixes, and resolving one problem can expose another. We introdu…
- arXiv cs.AIagentsGame-Creation-Agents: Autonomous Game Production
arXiv:2610.16776v1 Announce Type: new Abstract: Game-Creation-Agents (GCA) turns a natural-language request into a runnable Phaser 4 browser game. The pipeline first builds a multimodal game design document that couples…
- arXiv cs.AIagentsSame Operation, Different Permission: Evaluating Whether Guardrails Honor Authorization
arXiv:2610.16838v1 Announce Type: new Abstract: As language-model agents write code, move money and change records on behalf of users, deciding whether an action is authorized has become a central safety problem. Guardra…
- arXiv cs.AIagentsAcceptable Misalignment
arXiv:2610.16881v1 Announce Type: new Abstract: There is a specific challenge designers face in developing autonomous robots capable of open-ended learning. This challenge is how one can develop such systems in an ethica…
- arXiv cs.AIagentsObserve, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration
arXiv:2610.16895v1 Announce Type: new Abstract: LLMs are used as high-level controllers for embodied agents, but it remains unclear whether they support collaborative reasoning, such as anticipating a collaborator's acti…
- arXiv cs.AIagentsNeural Bayesian Networks for Modular and Scalable Decision-Making Under Uncertainty
arXiv:2610.16902v1 Announce Type: new Abstract: Bayesian Networks (BNs) are established tools for letting agents reason under uncertainty in sequential decision-making. They split a joint distribution into local conditio…
- arXiv cs.AIagentsAudit tools of the trade: Automated Auditor Elicitation Can Be Sensitive to the Context the Auditor Is Given
arXiv:2610.16911v1 Announce Type: new Abstract: Does providing additional context to automated AI auditors improve their effectiveness? Using the Petri tool to audit LLM coding agents, we test the impact of providing two…
- arXiv cs.AIagentsMADDIE: Multi-Agent Drug Discovery Engine
arXiv:2610.16975v3 Announce Type: replace Abstract: Drug discovery remains a resource-intensive and time-consuming process, involving billions of dollars and a decade of development to advance a drug to market. While man…
- arXiv cs.AIagentsPRAISE: A Reproducible Workflow for Non-Programmer Scientists to Implement Published AI Models
arXiv:2610.16980v1 Announce Type: new Abstract: Artificial Intelligence (AI) models are increasingly developed, published and used across scientific fields. Researchers, students and industry professionals who want to ap…
- arXiv cs.AIagentsGlasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch Agents
arXiv:2610.16998v1 Announce Type: new Abstract: Deep search enables language agents to solve complex information-seeking tasks through iterative web exploration. However, developing robust open-source agents remains chal…
- arXiv cs.AIagentsNeos: Learning to Interleave Search and Visual Reasoning
arXiv:2610.17043v1 Announce Type: new Abstract: Recent multimodal deep search agents have advanced tool use and visual content retrieval, yet they still struggle to convert intermediate visual evidence into actionable gu…
- arXiv cs.AIagentsWhen LLM Agents See a Conflict but Still Proceed: Cross-Domain Dependencies in Network Slicing
arXiv:2610.17118v1 Announce Type: new Abstract: Future AI-native networks are being designed to apply autonomous agents built on large language models (LLMs) in network management through intents. When intents from diffe…