LLM-based multi-agent systems exhibit remarkable collaborative capabilities in complex multi-step tasks. However, these systems are highly sensitive to single-step execution errors that can propagate through agent interactions and lead to cascading failures. To understand the causes of failure and improve system reliability, failure attribution has been introduced as a task that aims to automatically identify the root cause step responsible for a failure. Existing failure attribution methods mainly rely on LLMs to reason over original execution trajectories, which not only incur high inference costs and latency, but also suffer from interference caused by redundant and noisy execution logs, causing LLMs to struggle in accurately identifying the true root cause step. To address this, we propose StepFinder, a lightweight failure attribution framework. We use LLMs solely during the feature construction phase to encode execution logs into temporal semantic sequences. Subsequently, a parameter-efficient combination of temporal modeling and attention modules is applied to capture the sequential evolution and cross-step dependencies of the trajectories. Finally, the step-level error score is refined through multi-scale differences and position bias, enabling precise root cause identification. Experimental results on the Who&When benchmark demonstrate that StepFinder outperforms LLM-based methods in step-level failure attribution while achieving substantially higher inference efficiency, reducing inference time by 79% compared with the fastest LLM-based method, with no text generation overhead. Our code is available at https://github.com/taiyu-zhu/StepFinder.
DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；School of New Media and Communication, Tianjin University（天津大学新媒体与传播学院）；College of Computer Science and Artificial Intelligence, Fudan University（复旦大学计算机科学技术与人工智能学院）
Cascade Failure Attribution for Multi-Agent Systems
Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Error-Propagation Modeling for Failure Attribution in LLM-Based Multi-Agent Systems
College of Computer Science and Technology, National University of Defense Technology（国防科技大学计算机学院）；School of Mechanical Engineering, Tianjin University（天津大学机械工程学院）
From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；State Key Laboratory of Complex System Modeling and Simulation Technology（复杂系统建模与仿真技术国家重点实验室）；Science & Technology on Integrated Information System Laboratory（信息系统集成技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Wuhan University of Technology（武汉理工大学）
Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
MOE KLINNS Lab（MOE KLINNS实验室）；School of Computer Science and Technology（计算机科学与技术学院）；School of Cyber Science and Engineering（网络安全工程学院）；School of Software Engineering（软件工程学院）；School of Control Science and Engineering（控制科学与工程学院）；Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering（陕西省大数据知识工程重点实验室）；Laboratory for AI and New Forms of Education（人工智能与新型教育实验室）；Lenovo AI Technology Center, CTOO, Lenovo（联想AI技术中心，联想CTOO）；Sydney AI Centre, The University of Sydney（悉尼AI中心，悉尼大学）
HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI Systems
Harokopio University of Athens（雅典哈罗科皮奥大学）；Democritus University of Thrace（色雷斯德谟克利特大学）；University of Western Macedonia（西马其顿大学）；Athena Research Center（雅典娜研究中心）
DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
Institute of Neuroscience, State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Shanghai, 200031, China（中国科学院神经科学研究所、脑认知与脑启发智能技术重点实验室、脑科学与智能技术卓越中心、中国科学院、上海）；University of Chinese Academy of Sciences, School of Future Technology, Beijing, 100049, China（中国科学院大学、未来技术学院、北京）；Microsoft（微软公司）
Where Did It Go Wrong? Capability-Oriented Failure Attribution for Vision-and-Language Navigation Agents
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；Science & Technology on Integrated Information System Laboratory（信息集成信息系统实验室）；State Key Laboratory of Complex System Modeling and Simulation Technology（复杂系统建模与仿真技术国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Singapore Management University（新加坡管理大学）
GraphSkillAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback
National Key Laboratory for Novel Software Technology, Nanjing University（南京大学计算机软件新技术全国重点实验室）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）
Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
Department of Computer Science, University of South Dakota（南达科他大学计算机科学系）；School of Information and Artificial Intelligence, Yangzhou University（扬州大学信息与人工智能学院）
