Overview

Agent failure analysis examines how errors arise and spread in tool-using, coding, GUI, and multi-agent systems, including failures hidden by apparently successful final outcomes. Common approaches annotate execution trajectories, classify failure modes, monitor runtime behavior, and use dependency graphs or counterfactual replay to distinguish root causes from downstream symptoms. Benchmarks use real or human-labeled traces, controlled fault injection, and repeated runs to test diagnosis and recovery. A central challenge is making attributions genuinely causal and robust when logs are incomplete, task conditions vary, and benchmark shortcuts can make performance look stronger than it is.

Latest papers

CardsList

159 papers8 papers in the last four weeks, down 75% on the four weeks before. 0.1% of all new papers.

  1. Smart Home Agents Make Capable but Unpredictable Grid Operators

    Nov 13, 2026Christopher Terrazas, Eduardo Cotilla-SanchezAgent Failure AnalysisAI Agent Reliability

  2. Dependable Long-Horizon LLM Agents: A Trajectory-Centered Empirical Study of Where Errors Enter and Which Controls Reach Them

    Nov 9, 2026Shaohuang Wang, Jinghao Wen, Xulei Zhang +1Agent Failure AnalysisLLM Agent Reliability

  3. What Structurally Breaks an Agent? Auditing Difficulty in Stateful Tool-Use Workflows

    Nov 2, 2026Shereen Anand, Ju Wang, Yali DuAgent Failure AnalysisAI Agent Auditing

  4. When AI Agents Act on Our Behalf: A Taxonomy of Human-Agent Interaction Failure

    Oct 30, 2026Canwen Wang, Qing Xiao, Haiyi Zhu +1Agent Failure AnalysisHuman-AI Interaction

  5. Babysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures

    Oct 26, 2026Shravika Mittal, Sunnie S. Y. Kim, Scott Counts +3Agent Failure AnalysisAI Agent Reliability

  6. CUA-Recovery: Benchmarking Error Recovery in Long-Horizon Computer-Use Agents

    Oct 20, 2026Xu Hu, Haoming Li, Yuxiang Wang +11Computer-Use AgentsComputer-Use Agent Benchmarks

  7. MASIF: Implicit Failures for Process Observability in Multi-Agent Systems

    Oct 19, 2026Yanwei Huang, Arpit Narechania, Atanu SinhaMulti-Agent SystemsAgent Failure Analysis

  8. OmicsBench: a long-horizon multi-turn benchmark of AI agents on research-study-scale bioinformatics

    Oct 15, 2026Gideon Shaked, Siddharth NagisettyBioinformaticsAI Agent Benchmarks

  9. How GUI Agents Fail: GraceBench for Execution Stability Diagnosis

    Oct 14, 2026Ridong Zhang, Shuxian Liang, Chaoqun Wan +2Computer-Use Agent BenchmarksGUI Agents

  10. Why Do Agent Teams Fail Across Boundaries? A Failure Taxonomy for Agent-to-Agent Systems with Private States

    Oct 14, 2026Sarath Shekkizhar, Prathyusha Jwalapuram, Zixuan Ke +12Agent Failure AnalysisMulti-Agent Systems

  11. Executable Prefix Values for Locating Agent Failures

    Oct 13, 2026Bingyu Shen, Jiaqi Tang, Lan Wei +3Agent Failure AnalysisLLM Agent Evaluation

  12. Why Agentic Workflows Fail: A Taxonomy Derived from Literature and Empirical Data

    Oct 12, 2026Xin Li, Rami Bahsoon, Tao ChenAgent Failure AnalysisAgentic Workflows

  13. Structural Baselines Matter for Agent Failure Detection and Attribution

    Oct 12, 2026Ramesh Arvind Naagarajan, Stefan StreifAgent Failure AnalysisFailure Attribution for LLM Agents

  14. Can Failed Trajectories Reveal Where Agents Go Wrong? Agentic Failure Attribution Without Step-Level Labels

    Oct 9, 2026Do Nguyen-Thanh, Junlin Fang, Bing Li +2Failure Attribution for LLM AgentsAgent Failure Analysis

  15. Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems

    Oct 8, 2026Jiaqi Liao, Yuanzhao Zhai, Huanxi Liu +5Failure Attribution for LLM AgentsAgent Failure Analysis

  16. ReCast: Attribution-Oriented Step Representation Learning for LLM-Based Agent Systems

    Oct 8, 2026Weilin Jin, Mingyu Wang, Taiyu Zhu +7Failure Attribution for LLM AgentsAgent Failure Analysis

  17. From Evidence to Action: How Tool-Using Agents Fail

    Oct 6, 2026Hongzhan Lin, Shidong Cao, Ziyang Luo +3Agent Failure AnalysisEvidence-Grounded Reasoning

  18. Disentangling Task Difficulty from Run-Level Failure in Agent Failure Prediction

    Oct 4, 2026Mohsen EsfandyariDoulabi, Lawrence Arkoh, Biruk Tadesse +4Agent Failure AnalysisLLM Agent Evaluation

  19. StateWise: Diagnosing and Repairing Persistent Operational State Before Agent Actions

    Oct 4, 2026Yongyuan Peng, Zhou Feng, Tongying Wu +5Agent Failure AnalysisSoftware Engineering Agents

  20. DeFA: Dependency-Guided Failure Attribution for LLM Agents

    Oct 1, 2026Bo Deng, Xinlei Zheng, Yi Wei +6Agent Failure AnalysisLLM Agent Evaluation

  21. A Competing-Hazards Systematization of Loss of Control in Autonomous Agents

    Sep 29, 2026Mohamed Aly BoukeAgent Failure AnalysisAI Agent Auditing