AI news archive.
4,966 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsREFLEX with Jev for Efficient Selective Control in LLM Agents
arXiv:2609.26532v1 Announce Type: new Abstract: LLM agents often use generative models for bounded decisions, raising the question of when these decisions can be handled more efficiently without reducing task success. We…
- arXiv cs.AIagentsThe Delegation Blind Spot: Auditing Product Decisions from Agent Choices
arXiv:2609.26642v1 Announce Type: new Abstract: Successful agent execution need not identify which future product improvement its user would value. We present a decision-specific audit that maps a declared observation ch…
- arXiv cs.AIagentsGrow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents
arXiv:2609.26760v2 Announce Type: replace Abstract: Large language model (LLM) agents often handle streams of related tasks, yet standard harnesses repeatedly ask the model to reconstruct the same control decisions insid…
- arXiv cs.AIagentsSWE-Serve: Benchmarking Agentic Engineering For Production Inference Serving
arXiv:2609.26777v1 Announce Type: new Abstract: We introduce SWE-Serve, a benchmark for evaluating agents on production inference engineering tasks. Implementing an inference feature can require coordinating multiple cha…
- arXiv cs.AIagentsCliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents
arXiv:2609.26779v1 Announce Type: new Abstract: Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context windows. We develop C…
- arXiv cs.AIagentsAIBuildAI-2.5: Efficient Autonomous AI Model Development Through LLM-Guided Tree Search
arXiv:2609.25047v1 Announce Type: cross Abstract: Autonomous agents that automatically build artificial intelligence (AI) models could broaden access to AI across science and engineering. A popular line of such agents fr…
- arXiv cs.AIagentsSelf-Cleaning and Captured Anyway: One Measured Primitive for Error in a Store an Agent Writes to Itself, and What a Falling Score Actually Measures
arXiv:2609.25052v1 Announce Type: cross Abstract: "An agent that writes its conclusions into a store it later retrieves from closes a loop usually reported as one-way contamination. Taking the loop to the infinite-tenure…
- arXiv cs.AIagentsImpact Is Not Invalidation: Ask About the Claim, Not the Diff
arXiv:2609.25130v1 Announce Type: cross Abstract: Memory systems for coding agents must decide, when a repository changes, which of their stored claims have become false. Content anchoring invalidates a claim whenever th…
- arXiv cs.AIagentsQwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction
arXiv:2609.25176v2 Announce Type: replace-cross Abstract: Real-time voice assistants must reason over evolving requests, execute actions, and follow conversational rules. Qwen-Audio-3.1-Realtime brings these requirements…
- arXiv cs.AIagentsIndirect tipping: a social attack surface in AI agent populations
arXiv:2609.25194v1 Announce Type: cross Abstract: As generative AI agents are deployed at scale, safety will depend not only on technical safeguards and individual model design, but also on collective equilibria that det…
- arXiv cs.AIagentsTrains but Doesn't Learn: A Post-Training Delivery Benchmark for LLM Agents as Forward-Deployed Engineers
arXiv:2609.25237v1 Announce Type: cross Abstract: Post-training is becoming a service (PTaaS): a customer hands an operator data and a goal, and a forward-deployed engineer (FDE) returns a fine-tuned, evaluated, and depl…
- arXiv cs.AIagentsPasses Alone, Fails Together: Benchmarking Semantic Coordination in Parallel LLM-Agent Development
arXiv:2609.25396v1 Announce Type: cross Abstract: Parallel coding agents can produce patches that work alone but fail when merged. This happens when one agent changes an interface or rule that another agent still relies…
- arXiv cs.AIagentsBeyond Natural Language: An Agent-Native Language for Autonomous Science
arXiv:2609.25421v1 Announce Type: cross Abstract: As autonomous AI agents take on every stage of scientific inquiry, research output is expanding far beyond human review capacity. Yet scientific communication still relie…
- arXiv cs.AIagentsPredictive Uncertainty for Neural CAE Surrogates
arXiv:2609.25430v1 Announce Type: cross Abstract: Neural surrogates can substantially accelerate computer-aided engineering (CAE) workflows, but their use in design requires uncertainty estimates that remain meaningful a…
- arXiv cs.AIagentsTransformer-Informed Trajectory Optimization for Relative Motion in Cislunar Orbits
arXiv:2609.25460v1 Announce Type: cross Abstract: Autonomous spacecraft guidance and control requires a fast solution to non-convex trajectory optimization, which can be accelerated by providing a near-optimal initial gu…
- arXiv cs.AIagentsAkasicMEM: Governed Enterprise Memory for Agents
arXiv:2609.25563v1 Announce Type: cross Abstract: Agent memory enables enterprise agents to retain knowledge acquired during work and reuse it across tasks and agents, turning execution experience into persistent organiz…
- arXiv cs.AIagentsCogenPVG: Cognitive-Enhanced Reflective Multi-Agent Framework for Persuasive Video Generation
arXiv:2609.25821v1 Announce Type: cross Abstract: Persuasive video generation (PVG) is a valuable yet under-explored research topic. Despite the significant advances in multimodal content generation, AI-empowered automat…
- arXiv cs.AIagentsRisk-Aware Online Conformal State Probing
arXiv:2609.25889v1 Announce Type: cross Abstract: AI-based autonomous agents, typically hosted at data centers, must acquire state information from robots or edge devices in order to issue informed control decisions. Man…
- arXiv cs.AIagentsPolicy-Backed Selective Regeneration under Tainted Inter-Agent Communication
arXiv:2609.26072v1 Announce Type: cross Abstract: Inter-agent communication is essential to multi-agent language-model systems, yet a single message may combine task-critical information with instructions not authorized…
- arXiv cs.AIagentsSilent Sabotage: Internal State Triggered Backdoor Attacks on LLM-Powered Robotic Systems
arXiv:2609.26184v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into robotic control systems is enabling a new generation of autonomous agents capable of complex reasoning and planning.…
- arXiv cs.AIagentsWatchPoint: Executable User Feedback for Real-World Agentic Web Development
arXiv:2609.26204v1 Announce Type: cross Abstract: When a professional web developer's code fails a test, they do not simply re-read the stack trace. They open the application in a browser, click buttons, inspect computed…
- arXiv cs.AIagentsThe Disciplinary Language Transfer Problem: How Psychological Vocabulary Produces Governance Failures in AI Agent Deployment
arXiv:2609.26562v1 Announce Type: cross Abstract: The vocabulary used to describe AI agents in governance contexts -- learning, memory, values, compliance, identity, trust -- is borrowed from psychological and organizati…
- arXiv cs.AIagentsFrom Alignment to Access Control: A Framework for GenAI Policy Enforcement
arXiv:2609.26682v1 Announce Type: cross Abstract: Generative AI (GenAI) applications have flourished enabling users to chat with large language models, and to create agents to act on their behalf for a variety of tasks.…
- arXiv cs.AIagentsMeasuring the Serving Stack Instead of the Model: Hidden Confounds in Local Tool-Use Evaluation
arXiv:2609.26693v1 Announce Type: cross Abstract: A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action. We study how local…
- arXiv cs.AIagentsDoes AI Save Time on Product Design? A Randomized Controlled Experiment of AI Prompt-to-Design Workflows
arXiv:2609.26725v1 Announce Type: cross Abstract: AI tools for digital product design now offer prompt-to-design capabilities, allowing designers and their non-designer colleagues to create prototypes through conversatio…
- arXiv cs.AIagentsA2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem
arXiv:2609.26761v1 Announce Type: cross Abstract: Agents using the Model Context Protocol (MCP) rely on semantic matching to select tools from third-party servers, exposing a semantic supply-chain risk through attacker-c…
- arXiv cs.AIagentsSmall Language Models are the Future of Agentic AI
arXiv:2506.02153v3 Announce Type: replace Abstract: Large language models (LLMs) are often praised for exhibiting near-human performance on a wide range of tasks and valued for their ability to hold a general conversatio…
- arXiv cs.AIagentsEndoCogniAgent: Closed-Loop Agentic Reasoning with Self-Consistency Validation for Endoscopic Diagnosis
arXiv:2508.07292v4 Announce Type: replace Abstract: Endoscopic diagnosis is an iterative process in which clinicians acquire, compare, and verify local visual evidence before reaching a conclusion. Current AI systems do…
- arXiv cs.AIagentsDistributed Legal Infrastructure for a Trustworthy Agentic Web
arXiv:2603.06884v2 Announce Type: replace Abstract: The agentic web marks a structural transition from a human-centered information network to a digital environment populated by artificial intelligence (AI) agents that p…
- arXiv cs.AIagentsAgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
arXiv:2604.02947v2 Announce Type: replace Abstract: Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain s…
- arXiv cs.AIagentsSAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory
arXiv:2605.12061v2 Announce Type: replace Abstract: Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, whic…
- arXiv cs.AIagentsAgent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
arXiv:2606.06448v2 Announce Type: replace Abstract: LLM agents are increasingly deployed on long-horizon tasks requiring sustained reasoning over extended interaction histories. Realizing this at scale requires agents to…
- arXiv cs.AIagentsConfidence Composition for Multiagent Language Model Systems
arXiv:2606.13591v2 Announce Type: replace Abstract: Multiagent language model systems, such as collaborative reasoning and debate, produce multiple correlated candidate answers and confidence signals. However, these sign…
- arXiv cs.AIagentsSPINE: Bridging the Cyber-Physical Gap with Agentic AI
arXiv:2607.13049v2 Announce Type: replace Abstract: Foundation models give robots powerful high-level reasoning, yet turning that intelligence into reliable physical action remains difficult: roboticists must still align…
- arXiv cs.AIagentsSimulate to Generalize: Scaling Stateful Supervision for API-calling Agents using LLM World Models
arXiv:2607.16900v3 Announce Type: replace Abstract: Training agents that generalize to unseen, stateful environments requires a massive dataset of state-changing trajectories covering a vast and diverse set of APIs. Howe…
- arXiv cs.AIagentsDFAH-Bench: What Agreement Leaves Unmeasured in Financial Agents
arXiv:2607.20491v4 Announce Type: replace Abstract: When a financial agent repeats its decision, how much does that tell us about the actions behind it? DFAH-Bench examines this question through replay experiments, a con…
- arXiv cs.AIagentsImproving Constraint Models with LLM Agents
arXiv:2608.08127v2 Announce Type: replace Abstract: The runtime of Constraint Programming (CP) solvers is highly sensitive to modeling choices, such as symmetry breaking, implied constraints, global constraints, constrai…
- arXiv cs.AIagentsBixBench3: Benchmarking AI agents on research-study-scale computational biology tasks
arXiv:2608.25286v2 Announce Type: replace Abstract: Artificial intelligence (AI) promises to accelerate biological research by automating computational analyses. Yet the ability of AI agents to execute on computational b…
- arXiv cs.AIagentsMARBO: Relational Belief Grounding for LLM Agents in Social Deduction Games
arXiv:2609.06563v2 Announce Type: replace Abstract: Social deduction games (SDGs) require agents to reason under partial observability by maintaining relational beliefs about hidden roles and team alignments. While recen…
- arXiv cs.AIagentsWhat Does Multi-Agent Debate Actually Change?
arXiv:2609.08016v3 Announce Type: replace Abstract: Multi-agent debate, in which several LLMs exchange arguments before producing an answer, raises a basic question: does expressed disagreement reflect changes in the mem…
- arXiv cs.AIagentsELEMENT: Episodic and Lifelong Exploration via Maximum Entropy
arXiv:2412.03800v2 Announce Type: replace-cross Abstract: Reinforcement learning agents depend on reward signals whose density is rarely under the designer's control, and when such signals are absent, an agent must gener…
- arXiv cs.AIagentsWebArxiv: A Reproducible Benchmark for Evaluating Multimodal Web Agents on arXiv Tasks
arXiv:2507.00938v4 Announce Type: replace-cross Abstract: Foundation models now enable autonomous agents to interact with real-world websites, but existing benchmarks emphasize general-purpose browsing, underrepresent re…
- arXiv cs.AIagentsReal-time autonomous magnetic microrobot navigation across dynamic and biologically relevant environments
arXiv:2509.05500v2 Announce Type: replace-cross Abstract: Autonomous microrobots could enable minimally invasive interventions in confined biological environments, but their operation requires real-time navigation among…
- arXiv cs.AIagentsMulti-Agent Design Assistant for the Simulation of Inertial Fusion Energy
arXiv:2510.17830v3 Announce Type: replace-cross Abstract: Inertial fusion energy promises nearly unlimited, clean power if it can be achieved. However, the design and engineering of fusion systems requires controlling an…
- arXiv cs.AIagentsA Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
arXiv:2604.16548v5 Announce Type: replace-cross Abstract: The emergence of writable, cross-session persistent memory in LLM agents introduces a qualitatively different threat landscape from conventional input-centric sec…
- arXiv cs.AIagentsMechanism Design Is Not Enough: Prosocial Agents for Cooperative AI
arXiv:2605.08426v3 Announce Type: replace-cross Abstract: Ensuring that AI agents behave safely and beneficially when interacting with other parties has emerged as one of the central challenges of modern AI safety. While…
- arXiv cs.AIagentsThe Bystander Effect in Multi-Agent Reasoning: Quantifying Cognitive Loafing in Collaborative Interactions
arXiv:2605.10698v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) assume that collaborating inherently improves Large Language Model (LLM) reasoning. We challenge this by demonstrating that simulated so…
- arXiv cs.AIagentsAgenticDiffusion: Multi-View Reasoning with View-Conditioned Diffusion Planning for Vision-Based UAV Navigation
arXiv:2606.04111v2 Announce Type: replace-cross Abstract: Vision-based UAV navigation becomes challenging when navigation targets are distributed across complementary camera views and cannot be reliably observed from a s…
- arXiv cs.AIagentsHLSmith: An Expert-Guided Agentic Framework for C/C++-to-HLS Translation
arXiv:2608.06791v2 Announce Type: replace-cross Abstract: Application-specific FPGA accelerators offer substantial performance and energy-efficiency gains across many application domains, but developing them is costly, o…
- arXiv cs.AIagentsPlan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent Memory
arXiv:2609.03450v2 Announce Type: replace-cross Abstract: A model that inherits one-line memories may pull one archived source record before acting; a directive in the store can steer that pull: a pointer, a criterion or…