AI Agent Auditing

Ask about this topic

Momentum

38 papers in the last four weeks, up 1167% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 100

All topics
CardsList

  1. When Does Randomized Oversight Align AI Agents That Can Conceal?

    Sep 29, 2026Joshua S. Gans, Richard HoldenAlgorithmic AuditingAI Agent Auditing

    UNSW Business School

  2. Audit the Scaffold, Not the Checkpoint: A Stationarity Dichotomy for Recursive Self-Improvement in Agentic Coding

    Sep 28, 2026Sebastian Bobadilla-Suarez, Bob Suh, Ryan FortinSoftware Engineering AgentsAI Agent Auditing

    OnCorps

  3. DGF-Bench: A Benchmark for Simulating and Auditing Deception Against Multi-Agent Governance Boards

    Sep 28, 2026Jeremy CanaleAI Agent AuditingAI Agent Security Benchmarks

  4. Frozen Judges, Moving Agents: Version-Dependent LLM-Judge Error and the Limits of Judge-Assisted Agent Evaluation

    Sep 28, 2026Jiapeng LiLLM-as-a-JudgeAI Agent Auditing

  5. ReplayLens: Auditing Agents' Use of Outcomes

    Sep 28, 2026Dong Xu, Zhangfan Yang, Jiantao Wu +5AI Agent AuditingLLM Agent Memory

    School of Artificial Intelligence, Shenzhen University · EasternDawn · School of Computer Science, University of Nottingham Ningbo

  6. Opera: A Verbal Critic Framework for Long-horizon Coding Agents

    Sep 27, 2026Kai Mei, Zhiyuan Hu, Yutong Dai +7AI Coding AgentsAI Agent Auditing

    Salesforce AI Research · Rutgers University · Lehigh University

  7. Learning Strategies to Break Judges

    Sep 27, 2026Guruprerana Shabadi, Aaditya Naik, Rajeev Alur +1LLM-as-a-JudgeAI Agent Auditing

    University of Pennsylvania · Oracle

  8. LLM Agents Can Easily Tamper With Their Own Traces

    Sep 24, 2026Jeremy Qin, David Schmotz, Derck Prinzhorn +3AI Agent AuditingAI Agent Security

    ELLIS Institute Tübingen · Max Planck Institute for Intelligent Systems · Tübingen AI Center +3

  9. Reward Hacking Challenges Oversight of Autonomous Research Agents

    Sep 23, 2026Yue Huang, Zhangchen Xu, Yuchen Ma +12Reward HackingAI Agent Auditing

    Bake AI · University of Notre Dame · University of Washington +6

  10. Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning

    Sep 23, 2026Liu Hung MingReinforcement LearningAI Agent Auditing

    PARRAWA AI

  11. Don't Read the Log: Execution Traces Contaminate Verifiers in Video-Generation Agents

    Sep 23, 2026Jian XuLLM-as-a-JudgeAI Agent Auditing

    RIKEN

  12. Compliant AI Infrastructure for Regulated Finance: A tiered multi-agent framework with DLT audit trails for financial operations in DACH

    Sep 23, 2026Walter Kurz, Reinhard MaggAI Agent AuditingRuntime Enforcement for AI Agents

    Swissi Institute for AI

  13. Discover, Falsify, Revise: Auditing Input-Use Claims from Source Code to Predictive Contribution in Agent-Discovered Cell Models

    Sep 23, 2026Mengran Li, Bo Li, Chengyang Zhang +3AI Agents for Scientific DiscoveryAI Agent Auditing

    Sun Yat-sen University · University of Macau · Sichuan University +3

  14. The Delegation Blind Spot: Auditing Product Decisions from Agent Choices

    Sep 22, 2026Shivam GuptaAI Agent AuditingPartial Identification

    Independent Research

  15. The Disciplinary Language Transfer Problem: How Psychological Vocabulary Produces Governance Failures in AI Agent Deployment

    Sep 22, 2026Kymberly Lasser-Chere, Tyler Akidau, Marc MillstoneAI AccountabilityAI Agent Auditing

    Coastal Waters Healing Center, Surf City, NC, USA · Redpanda, Seattle, WA, USA

  16. PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?

    Sep 16, 2026Mika Okamoto, Ansel Kaplan ErolAI Agent AuditingLLM Agent Evaluation

    Georgia Institute of Technology · Decagon AI · Baseten

  17. Who Audits Whom, on What Substrate, with What Evidence? An Independence-Graded Audit Protocol for Agentic AI

    Sep 16, 2026Mohamed Chahine GhanemAI AssuranceAI Agent Auditing

    Keele University, School of Computer Science and Mathematics, Keele, United Kingdom · University of Liverpool, Cybersecurity Institute, Liverpool, United Kingdom

  18. Clean Scores, Buried Evidence, and Confident Wrong: A Receipt-Based Audit of Frontier Agentic QA

    Sep 14, 2026Luis M. SánchezData ProvenanceAI Agent Auditing

    Toryx Inc.

  19. HazardAuditor: From Executable Threats to Safer Computer-Use Agents

    Sep 14, 2026Yunhao Feng, Ruixiao Lin, Ming Wen +5Language Model Safety EvaluationAI Agent Auditing

    Ant Group · Hunan Institute of Advanced Technology · Zhejiang University +3

  20. The Mechanics of a Swarm: A Reproducible External Reconstruction of an Unintended Agent-Coordination Episode on a Third-Party Wiki

    Sep 14, 2026Philipp Lütje (Philflow, Schenefeld, Germany)Multi-Agent CoordinationAI Agent Auditing

    Philflow, Schenefeld, Germany

  21. OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows

    Sep 10, 2026Aayam Bansal, Keertan BalajiAI for ScienceAI Agent Auditing

  22. AgentAudit: An Open, Extensible Framework for Full-Lifecycle Trust Evaluation of AI Agents

    Sep 9, 2026Shrey Nag, Sachita, Abhishek Kumar Singh +2AI Agent ReliabilityAI Agent Auditing

    TIET · IGDTUW · GTBIT +1

  23. Audit Without Verification: When LLM Accountability Layers Relay Rather Than Check

    Sep 7, 2026Paul-Peter ArslanAgent Failure AnalysisAI Accountability

    Institute For Future Technologies

  24. Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents

    Sep 7, 2026Jingjie Ning, Shanshan Zhong, Xiaochuan Li +1AI Agents for Scientific DiscoveryAlgorithmic Auditing

    School of Computer Science, Carnegie Mellon University

  25. DNative-Twin: Decision Graphs and Digital Twins for Reconstructable Agentic Decisions

    Sep 3, 2026Junjie Pang, Zhenzhen Xie, Haoke Han +3Data ProvenanceAI Agent Auditing

    Qingdao University, Qingdao, China · Shandong University, Qingdao, China · Hangzhou Shujiao Technology Partnership (Limited Partnership), Hangzhou, China +1

  26. Agent Flight Recorder: Tamper-Evident Audit Trails with On-Chain Anchoring for Long-Horizon Tool-Using Agents

    Sep 1, 2026Laurent Bindschaedler, Quentin Botha, Christoph SiebenbrunnerData ProvenanceAlgorithmic Auditing

    Max Planck Institute for Software Systems · Research Institute for Cryptoeconomics, Vienna University of Economics and Business

  27. CatchBench: When Can an Agent Failure Be Caught?

    Aug 24, 2026Yue Zhao, Mengyuan Li, Ruolin Li +5Agent Failure AnalysisBenchmark Auditing

    University of Southern California · Carnegie Mellon University · AWS Agentic AI +3

  28. A2EA^2E : An End-to-End Agent Auditing Engine

    Aug 7, 2026Haoning Wang, Mingxun Zhang, Chenyue Yu +4Tool-Use EvaluationAI Agent Auditing

    Shanghai Artificial Intelligence Laboratory

  29. SearchAuditor: Auditing and Attributing Failures in Long-Horizon Search Agents

    Aug 5, 2026Zhixiang Liang, Yifei Liu, Yidan Huang +5Agent Failure AnalysisAI Agent Reliability

    University of Illinois Urbana-Champaign · 2Joy Future Academy, JD

  30. SkillTrace: Multi-Trace Provenance Auditing for LLM-Agent Skill Reuse

    Aug 5, 2026Jialuo Chen, Minghe Wang, Lingqi Jiang +7Data ProvenanceAI Agent Auditing

    Ant Group · Zhejiang University · Hangzhou Dianzi University, China +2