AI news archive.
4,958 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsFIRME: Registry-Anchored Memory Graphs for Evolving, Heterogeneous Investor Knowledge
arXiv:2610.40482v1 Announce Type: new Abstract: Financial AI workflows that reuse investor knowledge need persistent memory that integrates observations across sources and periods without losing identity or provenance. I…
- arXiv cs.AIagentsAgentic University: Collaborative Agents for Personalized Learning
arXiv:2610.40492v1 Announce Type: new Abstract: Large language models support personalized tutoring, content generation, and adaptive learning paths. However, capability development requires these resources and interacti…
- arXiv cs.AIagentsRetrieval as Traversal: Value-Indexed Memory for Stateful Long-Context Agents
arXiv:2610.40545v1 Announce Type: new Abstract: Long-context models repeatedly solve closely related retrieval problems. Attention or global retrieval can retain large stores, but each forward pass again searches for wha…
- arXiv cs.AIagentsAdvancing Clinical Genomic Analysis with a Skill-Centred Agent
arXiv:2610.40556v1 Announce Type: new Abstract: Clinical genomic analysis requires experts to integrate evolving guidelines, databases, and computational evidence. As sequencing has become increasingly accessible, this c…
- arXiv cs.AIagentsVeriCUA: Verification as Agentic Exploration for Computer-Using Agents
arXiv:2610.40578v1 Announce Type: new Abstract: Building and scaling computer-using agents (CUAs) across desktop, mobile, and web environments requires reliable task-completion verification for data curation, evaluation,…
- arXiv cs.AIagentsPre-Crime for Agents, at the Last Second: Probing When a Recruited Agent Gives In
arXiv:2610.40588v1 Announce Type: new Abstract: When AI agents share channels and credentials, one agent can press another to break its operator's rule, a first step towards collusion. Output filters check only what an a…
- arXiv cs.AIagentsCollaborative AI agents for autonomous experimental research with solid-state quantum spins
arXiv:2610.40589v1 Announce Type: new Abstract: An autonomous research laboratory could conduct an entire study, from formulating questions to preparing manuscripts. Artificial intelligence (AI) offers one route towards…
- arXiv cs.AIagentsCassette-Editor: A Video Editing Agent That Edits the Way You Do
arXiv:2610.37690v1 Announce Type: cross Abstract: Language agents increasingly work by calling tools on a persistent artifact, such as a code repository, and the result of each call shapes their next step. Video editing…
- arXiv cs.AIagentsNetwork Topology Does Not Matter: The Breakdown of Classical Consensus in LLM Populations
arXiv:2610.37699v1 Announce Type: cross Abstract: As multi-agent language model networks become widely deployed, predicting their collective behavior is a critical challenge. Classical distributed consensus theory relies…
- arXiv cs.AIagentsThe Coordination Tax and the Heterogeneity Dividend: Break-Even Conditions for Multi-Agent LLM Pipelines
arXiv:2610.37700v1 Announce Type: cross Abstract: Multi-agent LLM pipelines built on interoperability protocols such as the Open Floor Protocol (OFP) or A2A are usually justified on capability grounds, with their runtime…
- arXiv cs.AIagentsWhen Skills Tell Agents Not to Ask: A Large-Scale Study of Oversight Directives in Agent Skills
arXiv:2610.37734v1 Announce Type: cross Abstract: Agent skills, reusable instruction packages centred on a SKILL.md file, extend AI agents on demand, and a single line in a widely copied skill reaches every agent that lo…
- arXiv cs.AIagentsPoisoned Skills: Propagating Jailbreaks Through Agent Markdown Files
arXiv:2610.37738v1 Announce Type: cross Abstract: Modern agent frameworks allow users to provide Markdown files containing system prompts, tool descriptions, and skill definitions (e.g., SKILL.md), which are incorporated…
- arXiv cs.AIagentsLocating Sycophancy Across Training Stages in Open Language Models
arXiv:2610.37788v1 Announce Type: cross Abstract: Language model assistants sometimes change a correct answer when the user suggests a wrong one. The behavior, called sycophancy, is usually attributed to preference-based…
- arXiv cs.AIagentsScan Before You Install: Detecting and Mitigating Local and Composite Vulnerabilities in Skills
arXiv:2610.37901v1 Announce Type: cross Abstract: An agent skill packages natural-language instructions, scripts, and reference files that an LLM-based agent loads for a task. Skills may access the file system, shell, an…
- arXiv cs.AIagentsNemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI
arXiv:2610.38095v1 Announce Type: cross Abstract: We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context und…
- arXiv cs.AIagentsAnswer-Only Disclosure: Private-Context LLM Assistance over Web APIs with a Leakage Ledger
arXiv:2610.38126v1 Announce Type: cross Abstract: Web assistants increasingly answer questions about a user's private documents by pairing a small on-device model with a cloud LLM behind a Web API. In collaborative decod…
- arXiv cs.AIagentsScaling Lean Theorem Proving for Real-World Code Verification
arXiv:2610.38174v1 Announce Type: cross Abstract: We present EasyProver, a Lean proving system built from recursive agents with isolated contexts, asynchronous search, parallel tactic probing, and an elastic elaboration…
- arXiv cs.AIagentsIs it my preference? Role Grounding Attack against Agent's Memory via Social Interaction
arXiv:2610.38209v1 Announce Type: cross Abstract: LLM-based agents now share experiences on social platforms and remember new preferences to enhance their performance. However, existing memory systems contain a vulnerabi…
- arXiv cs.AIagentsSkeleton Coding: Program Structure as a Specification for Agents
arXiv:2610.38214v1 Announce Type: cross Abstract: Coding agents are typically provided end-to-end behavioral specifications that the code they produce should satisfy, such as tests and input--output examples. How many su…
- arXiv cs.AIagentsPrecedent or Intent? What Coding Agents Follow When Evolving Existing Code
arXiv:2610.38244v1 Announce Type: cross Abstract: Existing code reveals past implementation decisions but rarely explains the reasoning behind them. When coding agents implement new features or modify existing functional…
- arXiv cs.AIagentsVendster: An Evaluation Arena to Investigate How Forecasting Tool Quality Affects LLM Agent Behaviors in Buyer-Vendor Negotiation
arXiv:2610.38292v1 Announce Type: cross Abstract: Time-series forecasters are ranked almost entirely by accuracy metrics, but a forecast's decision value, its effect on the downstream decision, need not track accuracy an…
- arXiv cs.AIagentsEPSBench: Benchmarking LLM Agents for Earnings Forecasting
arXiv:2610.38293v1 Announce Type: cross Abstract: Quarterly earnings forecasting requires an agent to connect financial evidence to the income-statement line items that produce a company's reported earnings. We introduce…
- arXiv cs.AIagentsWhat Should a Navigator Remember? Spatiotemporal Memory for Zero-Shot Vision-Language Navigation
arXiv:2610.38318v1 Announce Type: cross Abstract: Zero-shot vision-and-language navigation (VLN) requires an agent to use past observations without navigation-specific training. We study what information an 8B-scale navi…
- arXiv cs.AIagentsA Case Study of a Multi-Agent Kernel-Optimization Loop That Learns a New AI Accelerator
arXiv:2610.38329v1 Announce Type: cross Abstract: Frontier large language models write correct CUDA kernels for most single-operator benchmark tasks, yet their accuracy collapses on accelerators whose architecture and pr…
- arXiv cs.AIagentsMUSE: Multi-Level Memory with Selective Runtime Injection for Scientific Coding Agents
arXiv:2610.38332v1 Announce Type: cross Abstract: Historical experience can guide scientific coding at multiple levels, but task-level retrieval may miss implementation lessons that become relevant during execution. We i…
- arXiv cs.AIagentsWeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video
arXiv:2610.38352v1 Announce Type: cross Abstract: Producing long-form videos from narration requires interdependent decisions that remain coherent across shots. Existing agentic editors often use multi-stage workflows dr…
- arXiv cs.AIagentsThe Code Behind the Layout: AI Agents for Analog Layout Generators
arXiv:2610.38426v1 Announce Type: cross Abstract: Analog layout remains largely manual and hard to automate. Generator frameworks such as gLayout express layouts as programs, producing layouts from parameterized, design-…
- arXiv cs.AIagentsRoleFUZZER: User-Behaviour Fuzzing for Role-Specification Adherence in Large Language Models
arXiv:2610.38438v1 Announce Type: cross Abstract: Large language models (LLMs) are often conditioned into specific roles such as tutors, interviewers, or agents acting for an organisation, through system prompts that spe…
- arXiv cs.AIagentsBenchmarking decision models against generative large language models on medical multiple-choice questions
arXiv:2610.38448v1 Announce Type: cross Abstract: Medical workflows often require selecting among predefined options. We compared 13 decision models with 15 generative large language model configurations, including diffe…
- arXiv cs.AIagentsTracekit Box: Running AI Agents in Micro-VMs Where Every Way Out Is Decided and Signed
arXiv:2610.38458v1 Announce Type: cross Abstract: AI agents now install packages, call model APIs with their operators' keys and change code in repositories that deploy to production. The network, credentials and write a…
- arXiv cs.AIagentsPersona Learning from Feedback for Personalized AI Assistants
arXiv:2610.38561v1 Announce Type: cross Abstract: Personalizing AI assistants requires adapting their behavior to users' preferences and task contexts. Existing work elicits assistant personas through persona prompting o…
- arXiv cs.AIagentsThe Artificial Personality Model: Theory, Implementation, Measurement and Experimental Validation in Conversational Agents
arXiv:2610.38608v1 Announce Type: cross Abstract: Artificial personality shapes user experience (UX) in human-machine interaction, yet coherent theoretical frameworks and validated measurement instruments remain limited.…
- arXiv cs.AIagentsHow Deterministic SAST and AI Security Agents Divide the Work: Coverage, Harness Policy and Cost in Snyk VulnBench 2.0
arXiv:2610.38617v1 Announce Type: cross Abstract: We ask what AI coding agents and AI security harnesses find that deterministic static application security testing (SAST) does not, and what they miss that SAST catches.…
- arXiv cs.AIagentsAtomTree: A Hierarchical Framework for State-Aware Embodied Instruction Following with LLMs
arXiv:2610.38744v1 Announce Type: cross Abstract: Embodied instruction following in interactive environments requires agents to interpret natural language commands and complete long-horizon tasks. Existing planners eithe…
- arXiv cs.AIagentsAutonomous Quantum Measurement with Agentic AI
arXiv:2610.38850v1 Announce Type: cross Abstract: Quantum materials exhibit diverse electronic and functional phenomena, but their characterization requires extensive experimental expertise, iterative decision-making and…
- arXiv cs.AIagentsMAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems
arXiv:2610.38946v1 Announce Type: cross Abstract: Training-time multi-agent system (MAS) design seeks to learn reusable orchestration policies, yet prevailing approaches remain largely one-shot: an Orchestrator generates…
- arXiv cs.AIagentsHERA: Assessing an Autonomous Agent for Quantum Device Measurement
arXiv:2610.39074v1 Announce Type: cross Abstract: Large language model agents have begun to carry out laboratory measurements, but their scientific conclusions are useful only if they hold up under scrutiny. Demonstratin…
- arXiv cs.AIagentsPCM: A Proof-Carrying Message Protocol for Verifiable Multi-Agent Communication
arXiv:2610.39109v1 Announce Type: cross Abstract: When one AI agent tells another that "the tests passed" or "a person approved this refund", the receiver has only the sender's word. A2A and MCP authenticate the channel,…
- arXiv cs.AIagentsAppreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection
arXiv:2610.39122v1 Announce Type: cross Abstract: Self-evolving personal agents act for users and learn from user feedback. However, if an agent obeys an instruction that an untrusted third party hides in content, the th…
- arXiv cs.AIagentsClean Sheets and Checkpoints: Evidence Complexity for Certifying Sequential Agent Risk
arXiv:2610.39124v1 Announce Type: cross Abstract: Dangerous-capability evaluations often test an AI agent from prepared states at ordered milestones. A clean sheet records no successes. What it certifies about a campaign…
- arXiv cs.AIagentsREALM: Identifying Minimal Task Assets for LLM Agents
arXiv:2610.39155v1 Announce Type: cross Abstract: Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Prompt injection turns this excess access into an oppor…
- arXiv cs.AIagentsEmbodiExp: Compositional Experience Transfer for Embodied Agents
arXiv:2610.39180v1 Announce Type: cross Abstract: Experience can help embodied agents turn high-level plans into grounded actions, but transferring it across tasks remains challenging: previously effective strategies may…
- arXiv cs.AIagentsLearning to Formulate: Agentic Hardware-Software Co-Design of AI Infrastructure through Progressive Optimization and Verification
arXiv:2610.39380v1 Announce Type: cross Abstract: AI infrastructure, the chips and software that train and serve AI models, is designed in layers. Layers make the system manageable, but they also fix which choices an opt…
- arXiv cs.AIagentsOPERA: OPamp Design by an Expert-Taught Reasoning Agent, from Specifications to Layout
arXiv:2610.39395v1 Announce Type: cross Abstract: Analog flows from specifications to a signed-off layout rarely run without manual iteration. Recent large language model (LLM) agents size circuits with optimizer loops o…
- arXiv cs.AIagentsWell-Specified and Well-Tested? Assessing SWE-bench-Style Datasets with a Self-Evolving Agent
arXiv:2610.39417v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong performance on software engineering (SE) tasks, driving the need for high-quality datasets for reliable training and evalua…
- arXiv cs.AIagentsSoei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering
arXiv:2610.39468v1 Announce Type: cross Abstract: AI coding agents now do long, multi-step and multi-session software work with little supervision. When a developer comes back to that work, the useful question is not wha…
- arXiv cs.AIagentsAgent-Wise Test-Time Normalization for Camera-Based Cooperative Perception with Corrupted Collaborators
arXiv:2610.39505v1 Announce Type: cross Abstract: Intermediate-fusion cooperative perception lets a vehicle detect objects beyond its own field of view by fusing features shared by nearby agents. When only a collaborator…
- arXiv cs.AIagentsJudging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy
arXiv:2610.39532v1 Announce Type: cross Abstract: Multi-agent LLM systems increasingly rely on persistent memory and inter-agent communication. These capabilities create privacy risks that extend beyond individual intera…
- arXiv cs.AIagentsLLM Agent-Based Design of RISC-V CPUs with FPGA-in-the-Loop Evaluation
arXiv:2610.39570v1 Announce Type: cross Abstract: Long-run RTL simulation of CPU candidates can take hours, while short diagnostic runs may miss performance degradation that emerges later in execution. This evaluation co…
- arXiv cs.AIagentsCan AI Agents Interface Clinicians and Complex Models?
arXiv:2610.39681v1 Announce Type: cross Abstract: Background: Contemporary healthcare institutions generate daily very large amounts of data, which contain highly useful information for the improvement of work organizati…