From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems
📖 Full Retelling
arXiv:2602.23701v1 Announce Type: new
Abstract: LLM-powered Multi-Agent Systems (MAS) have demonstrated remarkable capabilities in complex domains but suffer from inherent fragility and opaque failure mechanisms. Existing failure attribution methods, whether relying on direct prompting, costly replays, or supervised fine-tuning, typically treat execution logs as flat sequences. This linear perspective fails to disentangle the intricate causal links inherent to MAS, leading to weak observability
Entity Intersection Graph
No entity connections available yet for this article.
Original Source
--> Computer Science > Artificial Intelligence arXiv:2602.23701 [Submitted on 27 Feb 2026] Title: From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems Authors: Yawen Wang , Wenjie Wu , Junjie Wang , Qing Wang View a PDF of the paper titled From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems, by Yawen Wang and 3 other authors View PDF HTML Abstract: LLM-powered Multi-Agent Systems have demonstrated remarkable capabilities in complex domains but suffer from inherent fragility and opaque failure mechanisms. Existing failure attribution methods, whether relying on direct prompting, costly replays, or supervised fine-tuning, typically treat execution logs as flat sequences. This linear perspective fails to disentangle the intricate causal links inherent to MAS, leading to weak observability and ambiguous responsibility boundaries. To address these challenges, we propose CHIEF, a novel framework that transforms chaotic trajectories into a structured hierarchical causal graph. It then employs hierarchical oracle-guided backtracking to efficiently prune the search space via sybthesized virtual oracles. Finally, it implements counterfactual attribution via a progressive causal screening strategy to rigorously distinguish true root causes from propagated symptoms. Experiments on Who&When benchmark show that CHIEF outperforms eight strong and state-of-the-art baselines on both agent- and step-level accuracy. Ablation studies further confirm the critical role of each proposed module. Subjects: Artificial Intelligence (cs.AI) ; Software Engineering (cs.SE) Cite as: arXiv:2602.23701 [cs.AI] (or arXiv:2602.23701v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2602.23701 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Wenjie Wu [ view email ] [v1] Fri, 27 Feb 2026 06:08:42 UTC (1,505 KB) Full-text links: Access Paper: View a PDF...
Read full article at source