AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsOn the Effectiveness of Kernel-Level Evidence for Agent Security
arXiv:2609.28915v1 Announce Type: cross Abstract: LLM agents are deployed into infrastructure that grants them broad host authority, yet existing agent-security benchmarks and defenses operate almost exclusively at the a…
- arXiv cs.AIagentsCalibrated Decision Models for Autonomous Penetration-Testing Harnesses: JEV and Laya as System One Decision Layers for LLM-Driven Pentest Agents
arXiv:2609.28940v1 Announce Type: cross Abstract: Autonomous penetration-testing harnesses use large language models (LLMs) for reconnaissance, exploitation, and reporting, but often rely on those same models to confirm…
- arXiv cs.AIagentsBeneath the Scores: Rethinking Hallucination Evaluation for Video Understanding Models
arXiv:2609.28991v1 Announce Type: cross Abstract: Video understanding is increasingly performed by multi-stage LLM agents that separate temporal grounding, visual observation, and reasoning. Yet these stages are typicall…
- arXiv cs.AIagentsMulti-Agent Orchestration of 3GPP Channel Estimators
arXiv:2609.29044v1 Announce Type: cross Abstract: Pilot-aided channel estimation is a decisive block in orthogonal frequency-division multiplexing (OFDM) receivers for both 5G New Radio (5G-NR) and Long-Term Evolution (L…
- arXiv cs.AIagentsWhere Does Exactly-Once Live? Model, Harness, and Tool-Contract Effects on Duplicate Side Effects in LLM Agents
arXiv:2609.29095v1 Announce Type: cross Abstract: When a tool-using agent's write times out or returns a server error, the action may already have taken effect. Retrying blindly duplicates it -- a second charge, a second…
- arXiv cs.AIagentsHarnessPAI: An Evolving Harness for Physical AI
arXiv:2609.29166v2 Announce Type: replace-cross Abstract: Physical AI aims to build embodied agents that perceive the world, understand and reason about it, and decide how to act. Yet the field has focused primarily on t…
- arXiv cs.AIagentsSARFusion: Scene-Aware Routing Fusion for Robust Camera-LiDAR 3D Object Detection
arXiv:2609.29235v1 Announce Type: cross Abstract: Camera-LiDAR fusion has become a prevailing paradigm for 3D object detection in autonomous driving. However, existing fusion detectors often establish strong inter-modali…
- arXiv cs.AIagentsDocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents
arXiv:2609.29309v1 Announce Type: cross Abstract: In open-ended problem solving, collaborators often rely on discussion to surface concerns, challenge perspectives, and refine shared work as it evolves. While AI agents a…
- arXiv cs.AIagentsagentic-ger: terminology recovery in long-form speech using global context
arXiv:2609.29428v1 Announce Type: cross Abstract: Recent advances in speech language models have improved automatic speech recognition (ASR) for long-form audio. However, accurately and consistently transcribing domain-s…
- arXiv cs.AIagentsIterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis
arXiv:2609.29444v1 Announce Type: cross Abstract: Deep search requires LLM agents to decompose complex queries, search for evidence, and synthesize grounded answers, yet existing ReAct-style agents suffer from two limita…
- arXiv cs.AIagentsWhen Agents Act Unwatched: The Reduced-Supervision Paradox in Agentic AI
arXiv:2609.29547v1 Announce Type: cross Abstract: Agentic AI is sold on a simple promise: the system keeps acting when the user stops watching. That promise creates an accountability inversion. As stepwise supervision re…
- arXiv cs.AIagentsAgentKernel: The Trust-Native Agentic Operating System
arXiv:2609.29647v1 Announce Type: cross Abstract: Modern AI agents routinely cross trust boundaries: they ingest untrusted content, combine it with privileged instructions, persist intermediate beliefs in long-term memor…
- arXiv cs.AIagentsGraph, Loop, and Harness Engineering for Zero-Trust Agentic Data Engineering and Analytical Processing
arXiv:2609.29668v1 Announce Type: cross Abstract: Large language model agents increasingly automate data workflows, but end-to-end cloud data engineering and analytical execution require reliable coordination across code…
- arXiv cs.AIagentsUnderstanding and Exploiting Initialization Anchoring Weakness in Feedback-Based Agent Planning
arXiv:2609.29697v1 Announce Type: cross Abstract: Feedback-based planning improves agent reliability by incorporating tool observations and corrective feedback. However, its protection may not be distributed uniformly ac…
- arXiv cs.AIagentsPPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides
arXiv:2609.29718v2 Announce Type: replace-cross Abstract: Coding agents are increasingly moving beyond text-based software tasks to reconstruct visual targets through code. This capability, visual coding, requires agents…
- arXiv cs.AIagentsHard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution
arXiv:2609.29808v2 Announce Type: replace-cross Abstract: In July 2026, an unconstrained autonomous agent participating in a frontier AI cybersecurity evaluation harness breached its evaluation sandbox, established an ex…
- arXiv cs.AIagentsS2Planner: Multi-Scale Semantic Planner for End-to-End Autonomous Driving
arXiv:2609.29813v1 Announce Type: cross Abstract: We present S2Planner, a trajectory planner that combines three front-facing cameras with ego-motion history and the current driving command. A fine-tuned DINOv3 backbone…
- arXiv cs.AIagentsWorking with Agentic `Teammates': When a New Organizational Actor Collides with the Human Ecosystem of Work
arXiv:2609.29901v1 Announce Type: cross Abstract: Enterprise AI is transitioning from single-user, reactive tools toward proactive, multi-user 'teammates,' but our empirical understanding of this transition is limited. I…
- arXiv cs.AIagentsWorld Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal
arXiv:2609.29964v1 Announce Type: cross Abstract: General-purpose vision-language models (VLMs) bring broad knowledge and spatial reasoning to robot manipulation, yet existing systems either use them indirectly, to predi…
- arXiv cs.AIagentsGuardrails or Roadblocks? Effects of Pedagogical Style and Context Awareness in AI Teaching Assistants for Programming
arXiv:2609.29995v1 Announce Type: cross Abstract: AI teaching assistants (AI TAs) backed by large language models (LLMs) and pedagogical guardrails are increasingly being integrated into programming courses, providing st…
- arXiv cs.AIagentsEra by Eon: Benchmarking Enterprise Agents on Hidden Knowledge
arXiv:2609.30055v1 Announce Type: cross Abstract: In the Era by Eon benchmark, each question states the rules for its answer, and code computes the answer from a generated company's data. When agents can run code, the fo…
- arXiv cs.AIagentsKernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization
arXiv:2609.30059v2 Announce Type: replace-cross Abstract: Deep learning inference and training performance depends critically on GPU kernel efficiency. Modern compilers such as PyTorch Inductor automatically generate GPU…
- arXiv cs.AIagentsInstrumental Monitor Evasion Emerges Under Ordinary Task Pressure
arXiv:2609.30217v1 Announce Type: cross Abstract: A central concern in AI safety is that agents may treat oversight as an obstacle when it conflicts with completing their goals. We study instrumental evasion, the propens…
- arXiv cs.AIagentsCoding Agents for Generalized Task and Motion Planning Problems
arXiv:2609.30233v1 Announce Type: cross Abstract: Task and motion planning (TAMP) problems remain difficult even with full observability and object-centric states because discrete decisions are tightly coupled to geometr…
- arXiv cs.AIagentsRAPID: Robot Agentic Programming from Demonstrations
arXiv:2609.30249v1 Announce Type: cross Abstract: Coding agents have demonstrated enormous success in solving complex programming problems. To leverage their potential for robot systems, this work introduces Robot Agenti…
- arXiv cs.AIagentsLLM Agents Can Easily Tamper With Their Own Traces
arXiv:2609.30266v1 Announce Type: cross Abstract: Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents…
- arXiv cs.AIagentsDecoding ML Decision: An Agentic Reasoning Framework for Large-Scale Ranking System
arXiv:2602.18640v4 Announce Type: replace Abstract: Modern large-scale ranking systems operate within a sophisticated landscape of competing objectives, operational constraints, and evolving product requirements. Progres…
- arXiv cs.AIagentsMOOSEnger: A Simulation-Aware AI Agent Framework for the MOOSE Ecosystem
arXiv:2603.04756v3 Announce Type: replace Abstract: MOOSEnger is a modeling and simulation AI agent framework for the Multiphysics Object-Oriented Simulation Environment (MOOSE) ecosystem, built around a simulation-aware…
- arXiv cs.AIagentsBenchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork
arXiv:2605.24423v3 Announce Type: replace Abstract: In-Context Reinforcement Learning (ICRL) has enabled foundation agents to adapt instantaneously to novel tasks, yet its efficacy in Ad-Hoc Teamwork (AHT)-where coordina…
- arXiv cs.AIagentsMetrics That Write Themselves: Evolving an Evaluator from Its Own Blind Spots
arXiv:2608.18744v2 Announce Type: replace Abstract: Agents improve quickly against a reliable automatic metric and stall without one, and the applications that need them most, report generation among them, are the ones n…
- arXiv cs.AIagentsHuman Agreement and Return Association Are Not Interchangeable Criteria
arXiv:2609.11144v2 Announce Type: replace Abstract: Financial NLP has a standard workflow: validate a sentiment tool against human labels, then trust it to extract market signal. This assumes the two evaluations measure…
- arXiv cs.AIagentsThe Convention Gap: Beyond Literal Content in Human-AI Cooperation
arXiv:2609.11489v4 Announce Type: replace Abstract: Cooperative AI agents are often evaluated against other AIs, yet human cooperation is thought to rely on implicit conventions: shared rules for reading meaning beyond t…
- arXiv cs.AIagentsVibe Patenting: Evaluating LLM Judges for Professional Patent-Drafting Agents
arXiv:2609.13422v2 Announce Type: replace Abstract: LLM judges are increasingly used to evaluate and improve AI-generated outputs, yet their reliability for complex professional work remains unclear. We study this proble…
- arXiv cs.AIagentsThe Troy Moment: How LLM Agents Adjudicate the Decision Point Under Impossible Tasks, Claimed Authority, and Peer Information
arXiv:2609.15494v3 Announce Type: replace Abstract: Recent investigations of the July 2026 OpenAI-Hugging Face incident motivate two questions about agent behavior under task failure: when an assigned task becomes imposs…
- arXiv cs.AIagentsSheetMind: Actions Set Accuracy, Agents Set the Failure Mode
arXiv:2506.12339v3 Announce Type: replace-cross Abstract: Spreadsheet agents are converging on elaborate multi-agent designs, yet it is unclear how much of their performance comes from the agents rather than from the act…
- arXiv cs.AIagentsIDRBench: Benchmarking the Interactive Capabilities of Deep Research Agents
arXiv:2601.06676v3 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based deep research agents perform multi-step reasoning, web exploration, and long-form report generation. In these long-horizon workfl…
- arXiv cs.AIagentsMPFlow: Multi-modal Posterior-Guided Flow Matching for Zero-Shot MRI Reconstruction
arXiv:2603.03710v4 Announce Type: replace-cross Abstract: Zero-shot MRI reconstruction relies on generative priors, but single-modality unconditional priors produce hallucinations under severe ill-posedness. In many clin…
- arXiv cs.AIagentsNovelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning
arXiv:2603.11351v3 Announce Type: replace-cross Abstract: In dynamic open-world environments, autonomous agents often encounter novelties that hinder their ability to find plans to achieve their goals. Specifically, trad…
- arXiv cs.AIagentsDetecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented Scanning
arXiv:2603.17174v2 Announce Type: replace-cross Abstract: Code generation large language models (LLMs) are increasingly integrated into modern software development workflows. Recent work has shown that these models are v…
- arXiv cs.AIagentsAgileLog: A Forkable Shared Log for Agents on Data Streams
arXiv:2604.14590v3 Announce Type: replace-cross Abstract: In modern data-streaming systems, alongside traditional programs, a new type of entity has emerged that can interact with streaming data: AI agents. Unlike tradit…
- arXiv cs.AIagentsInterpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow
arXiv:2605.21980v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) represent a significant leap towards empathetic agents, demonstrating remarkable capabilities in emotion understanding. Howev…
- arXiv cs.AIagentsNVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation
arXiv:2606.03159v3 Announce Type: replace-cross Abstract: As autonomous vehicle capabilities advance, the safe evaluation of driving policies in long-tail scenarios remains a critical bottleneck. In closed-loop simulatio…
- arXiv cs.AIagentsAnalyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems
arXiv:2606.20470v4 Announce Type: replace-cross Abstract: Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with other agents…
- arXiv cs.AIagentsCryptographically verifiable authorization for autonomous AI agents: a falsifiable hypothesis and proof of concept
arXiv:2607.21325v3 Announce Type: replace-cross Abstract: Autonomous AI agents increasingly execute actions, invoke tools, and operate on protected resources with limited human oversight. Existing authentication and auth…
- arXiv cs.AIagentsTrident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)
arXiv:2608.04317v2 Announce Type: replace-cross Abstract: Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated almost exclusively…
- arXiv cs.AIagentsHardware Keystores for AI Agent Signing Workflows: A Zero-Trust MCP Enforcement Architecture
arXiv:2608.06130v2 Announce Type: replace-cross Abstract: AI agents increasingly sign Git commits, certify documents, and attest release artifacts on behalf of their operators, using private keys that live in software-ac…
- arXiv cs.AIagentsCalibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling
arXiv:2609.00949v2 Announce Type: replace-cross Abstract: Multi-turn tool calling is a core evaluation scenario for large language model (LLM) agents. On public tool-calling benchmarks, open-weight models now approach or…
- AI BusinessagentsCoreWeave connects AI coding tools to infrastructure intelligence
The neocloud vendor provides AI agents with access to data from its infrastructure management platform, helping developers troubleshoot slow or underperforming AI workloads.
- Simon Willison's WeblogagentsNote on 24th September 2026
The more time I spend working with coding agents, the more convinced I am that they make software engineering even harder. We can do amazing things with them, but unlocking their full potential requires extraordinary dis…
- Engadget AIagentsGoogle adds creepy avatars to Gemini 3.8 live's agents
Google has introduced Gemini 3.8 live avatars designed for customer service and other tasks.