AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsReinforcement Learning with Verifiable Rewards for Small Search Agents
arXiv:2609.28765v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) performs well on problems with clear rewards, such as mathematics and coding, but whether it also works where the rewa…
- arXiv cs.AIagentsAgent Memory with Episodic Retrieval for Financial Decision-Making
arXiv:2609.28771v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong capabilities in financial analysis and reasoning, inspiring recent advances in agent-based trading frameworks. While t…
- arXiv cs.AIagentsRECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?
arXiv:2609.28850v1 Announce Type: new Abstract: Reproducing a machine learning paper involves most research steps, from installing software and debugging to running experiments, work that AI agents increasingly do. We in…
- arXiv cs.AIagentsForecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents
arXiv:2609.28876v2 Announce Type: replace Abstract: Forecasting requires large language model (LLM) agents to gather evolving evidence, revise their beliefs, and make calibrated predictions over time. Yet evaluating and…
- arXiv cs.AIagentsHarness Tokenomics: A Router for the Enterprise Agentic Control Plane
arXiv:2609.28919v2 Announce Type: replace Abstract: Harnesses, the products that run AI coding agents, are multiplying, and enterprises are rolling them out to their employees. What started as pilots with a few hundred s…
- arXiv cs.AIagentsBack to the Definition: Estimating Step-Level Advantages via Trajectory Graphs for Agentic Reinforcement Learning
arXiv:2609.28963v1 Announce Type: new Abstract: Group-based reinforcement learning (RL) methods, such as GRPO and its variants, have become a leading paradigm for training reasoning and agentic large language models (LLM…
- arXiv cs.AIagentsWhen Does Action Credit Need Updating?
arXiv:2609.29007v1 Announce Type: new Abstract: Tool-using agents are continually updated with new interaction data. After each policy update, however, previously estimated action credits may become stale. Recomputing th…
- arXiv cs.AIagentsAlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining
arXiv:2609.29014v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems can automate alpha factor mining, but their reliance on external APIs limits control over cost, availability, and confi…
- arXiv cs.AIagentsMeshHeal: Two-Timescale Self-Healing for Gray Failures in Decentralized LLM Agent Networks
arXiv:2609.29015v1 Announce Type: new Abstract: Decentralized LLM-based multi-agent systems coordinate through local interactions, but an agent can remain responsive while its task-solving quality persistently degrades.…
- arXiv cs.AIagentsSLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL
arXiv:2609.29050v1 Announce Type: new Abstract: Tool-calling agents produce heterogeneous outputs, interleaving structured tool invocations with user-facing natural language summaries. This output heterogeneity presents…
- arXiv cs.AIagentsFrom Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents
arXiv:2609.29051v2 Announce Type: replace Abstract: On-policy self-distillation (OPSD) has become a popular recipe for post-training LLM agents. It supervises the agent model at the token level with a stronger teacher vi…
- arXiv cs.AIagentsScope Before You Persist: Preventing Cross-Family Interference in Agent Memory
arXiv:2609.29144v1 Announce Type: new Abstract: Persistent memory lets language-model agents improve prompts and skills without updating model weights. We show that matching retrieval scope to certification scope enables…
- arXiv cs.AIagentsA Wrong Turn Does Not Ruin the Journey: Deviation-Guided Skill Self-Evolution for LLM Agents
arXiv:2609.29154v1 Announce Type: new Abstract: Large language model agents increasingly rely on natural-language skills to solve complex tool-use tasks. However, such tasks often admit multiple valid solution paths, mak…
- arXiv cs.AIagentsIndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking
arXiv:2609.29167v1 Announce Type: new Abstract: Banking assistants must use account-specific information to answer requests and, in many cases, take actions through tools. Evaluating only the final response misses import…
- arXiv cs.AIagentsWhen Honesty is Not Enough in AI Debate
arXiv:2609.29189v1 Announce Type: new Abstract: Scalable oversight aims to verify the behaviour of agents whose capabilities exceed those of their overseers. AI debate has been proposed as an oversight solution in which…
- arXiv cs.AIagentsASIRF: An Agentic Framework for Context-Dependent Sensitive Information Redaction
arXiv:2609.29191v1 Announce Type: new Abstract: Sensitive information is defined by domain and intent, not a universal category, yet redaction systems such as privacy filters and named-entity recognizers fix a taxonomy a…
- arXiv cs.AIagentsTowards An LLM-Driven Unified Conversion Framework for BT and FSM in Autonomous Intelligent Systems
arXiv:2609.29228v1 Announce Type: new Abstract: Finite state machine (FSM) and behavior trees (BT) are widely adopted behavioral modeling paradigms for autonomous intelligent systems. While functionally equivalent and in…
- arXiv cs.AIagentsPolicy as Code: A Coroutine-Bridge Harness for Fast-Reasoning Reliability on CAR-bench
arXiv:2609.29251v1 Announce Type: new Abstract: CAR-bench evaluates whether tool-using agents stay reliable under real-world uncertainty, executing every tool inside the evaluator so that each tool-result exchange is a s…
- arXiv cs.AIagentsSkinAgent AI: A Safety-Grounded Multimodal Agentic Framework for Non-Diagnostic Skincare Support
arXiv:2609.29341v1 Announce Type: new Abstract: Consumer-facing skincare AI must coordinate visual evidence, product information, tool use, and user-facing actions within explicit evidence and safety boundaries. This stu…
- arXiv cs.AIagentsEpistemic-Probabilistic Model for Guarded Multi-Agent LLM Coordination
arXiv:2609.29366v1 Announce Type: new Abstract: Multi-agent large language models (LLMs) have become ubiquitous in applied AI, yet their theoretical foundations remain surprisingly understudied. Viewed through the lens o…
- arXiv cs.AIagentsSWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories
arXiv:2609.29465v3 Announce Type: replace Abstract: Large language model based coding agents have made substantial progress on repository-level software engineering tasks. Existing repository benchmarks, however, usually…
- arXiv cs.AIagentsEvaluation of Multi-Turn Consistency in LLM Agents: Survival Analysis and Failure-Rationale Taxonomy
arXiv:2609.29508v1 Announce Type: new Abstract: Large language model (LLM) agents may perform well on isolated tasks yet drift into inconsistency over extended interaction. We evaluate temporal consistency in a controlle…
- arXiv cs.AIagentsDelay-of-Gratification as a Multi-Agent Survival Micro-benchmark for Long-Horizon LLMs: Social Exposure, Personas, and Tool Use Budgets
arXiv:2609.29509v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as multi-turn agents that must sustain goals, use tools, and adapt to other agents over extended interactions. Howeve…
- arXiv cs.AIagentsStale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races
arXiv:2609.29522v1 Announce Type: new Abstract: Tool-using language-model agents increasingly mutate schedulers, data pipelines, object stores, and access-control systems. Between an agent's read and its commit, external…
- arXiv cs.AIagentsSafe Skill Retirement for Physical Agents
arXiv:2609.29543v1 Announce Type: new Abstract: Agent skills bundle procedural guidance with execution conditions governing authority, user consent, and live environment state. When model capabilities advance, maintainer…
- arXiv cs.AIagentsERRAND: Budgeted Maintenance of Agent Memory
arXiv:2609.29545v1 Announce Type: new Abstract: Deployed agents run on handed-over knowledge: a frozen policy consults a briefing of consolidated items written before the stream begins. The world then moves while the sto…
- arXiv cs.AIagentsPartHackBench: Certified Equal-Progress Stress Tests for Partial-Credit Tool-Agent Evaluation
arXiv:2609.29578v1 Announce Type: new Abstract: Long-horizon tool agents often make useful progress without reaching terminal success, motivating partial-credit evaluation. Yet evaluators may reward milestones that were…
- arXiv cs.AIagentsIngest-Time Fact Compilation for Cost-Efficient and Reliable Question Answering over Revised Corpora
arXiv:2609.29661v1 Announce Type: new Abstract: Most agentic question answering (QA) systems do an important part of their semantic work at the worst possible time: every time someone asks a question. When a corpus conta…
- arXiv cs.AIagentsBreaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments
arXiv:2609.29773v2 Announce Type: replace Abstract: Many real-world tasks (e.g., office workflows, scientific experimentation) require LLM agents to interact repeatedly with their environments for context-dependent opera…
- arXiv cs.AIagentsPUBG Ally: A Conversational Embodied Agent as an AI Teammate
arXiv:2609.29837v2 Announce Type: replace Abstract: We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teammate. Building su…
- arXiv cs.AIagentsWhen Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression
arXiv:2609.29875v1 Announce Type: new Abstract: Long horizon language model agents continually accumulate reasoning history, increasing context length and inference cost even after earlier decisions have been executed an…
- arXiv cs.AIagentsQwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents
arXiv:2609.29892v1 Announce Type: new Abstract: The rapid progression of large language models is extending AI from passive content generation into the active workflows of engineering and scientific discovery. This shift…
- arXiv cs.AIagentsWho Holds the Pen? Let Specifications, Not Agents, Sign Off
arXiv:2609.29921v1 Announce Type: new Abstract: Large language model agents increasingly combine generation, decision-making, execution, and self-evaluation within a single agentic loop. Although they operate under exter…
- arXiv cs.AIagentsAdvancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems
arXiv:2609.30001v1 Announce Type: new Abstract: Sustaining industrial recommendation research requires using the results of one experiment to decide what to investigate next. We present AgentX-Model, the next generation…
- arXiv cs.AIagentsSynthetic Hospital: An Open, Verifiable, Physician-Validated Longitudinal EHR Benchmark
arXiv:2609.30027v2 Announce Type: replace Abstract: Frontier language models are rarely used in clinical workflows because the realistic, longitudinal benchmarks needed to develop them are scarce. Real electronic health…
- arXiv cs.AIagentsHow does Adversarial Influence Scale in Multi-Agent Systems?
arXiv:2609.30028v2 Announce Type: replace Abstract: Multi-agent deliberation can improve performance, but what happens when some agents do not act in good faith? In practice, an agent may be deceptive and work to subvert…
- arXiv cs.AIagentsPrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations
arXiv:2609.30094v2 Announce Type: replace Abstract: Large language models increasingly operate as persistent assistants in user-facing, shared-session, and tool-augmented settings. When users disclose sensitive informati…
- arXiv cs.AIagentsHEXIS: Compiling Agent Skills into Extended Finite State Machines
arXiv:2609.30123v2 Announce Type: replace Abstract: Agent skills provide instructions and reusable knowledge, yet agents have to frequently infer which action to take next. This skill's execution paradigm combines task r…
- arXiv cs.AIagentsScreen Before You Serve: Simulation for Production Customer Experience AI Agents at 140M Scale
arXiv:2609.30137v1 Announce Type: new Abstract: Customer experience (CX) agents use tools and large language models to address customer requests and guide conversational interactions with an organization's products. Impr…
- arXiv cs.AIagentsGRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI
arXiv:2609.30147v1 Announce Type: new Abstract: Large Language Models (LLMs) typically exhibit a performance profile where reliability degrades as task complexity increases. We address the challenge of generating high-qu…
- arXiv cs.AIagentsJev-Mobile: Jev as an Executor for Mobile GUI Agents
arXiv:2609.30186v1 Announce Type: new Abstract: Vision-language models (VLMs) have become a common foundation for autonomous mobile GUI agents, but most existing systems rely on the VLM for both planning and action groun…
- arXiv cs.AIagentsA Living Benchmark for Information Retrieval from Electronic Health Records
arXiv:2609.30205v2 Announce Type: replace Abstract: Large language model (LLM)-based clinical assistants are increasingly being integrated into electronic health record (EHR) systems, transforming how clinicians retrieve…
- arXiv cs.AIagentsCertified Task-Conditioned Active Observability
arXiv:2609.28520v1 Announce Type: cross Abstract: Before acting upon an unobservable physical system, an autonomous agent must determine which latent distinctions govern downstream tasks, how many active interventions ar…
- arXiv cs.AIagentsWho Is Behind the Harness? Fingerprinting LLMs through Agentic Behavior
arXiv:2609.28559v1 Announce Type: cross Abstract: LLMs increasingly operate through coding-agent harnesses that inspect repositories, invoke tools, and modify files. Substituting the model behind such an agent can theref…
- arXiv cs.AIagentsWhere Cyber Agents Struggle: Bottleneck Analysis of Multi-Stage LLM Agents
arXiv:2609.28572v1 Announce Type: cross Abstract: Multi-stage LLM-based cyber agents may complete attack workflows while remaining brittle, costly, or reliant on incorrect interpretations of execution evidence. Success r…
- arXiv cs.AIagentsPersistent Billable State: Denial-of-Wallet Attacks and Defenses in Tool-Calling LLM Agents
arXiv:2609.28585v1 Announce Type: cross Abstract: Multi-step tool-calling LLM agents rely on host runtimes to preserve state across turns. When a runtime carries an external tool return into later model inputs, providers…
- arXiv cs.AIagentsDecision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions
arXiv:2609.28613v1 Announce Type: cross Abstract: Most studies of prompt injection focus on generative agents, leaving their effects on models with schema-defined outputs unclear. We examine these effects in Jev, a non-g…
- arXiv cs.AIagentsPolicy Complexity, Reaction Time, and Bounded Rationality in Reinforcement Learning
arXiv:2609.28737v1 Announce Type: cross Abstract: Biological agents do not learn under conditions of unlimited computation. For humans, learning and choice are shaped by constraints on perception, attention, and working…
- arXiv cs.AIagentsBlockchain-Enabled Artificial Intelligence and AI Agents for Secure Data Sharing and Cybersecurity Applications
arXiv:2609.28843v1 Announce Type: cross Abstract: Blockchain and artificial intelligence (AI) are converging into a single infrastructural layer for securing data sharing, model integrity, and autonomous decision-making…
- arXiv cs.AIagentsPersuaded, Not Informed: Incentive-Misaligned Witnesses Defeat In-Context Grounding
arXiv:2609.28854v1 Announce Type: cross Abstract: Language-model agents increasingly answer questions over customer-relationship management (CRM) records, such as whether to qualify a sales lead. We identify a failure mo…