arXiv cs.AI· Xiaoguang Guo, Yaohao Long, Chuxu Zhang·· 3 天前AI 评分29
BLADE：面向 LLM 多智能体系统失败归因的信息使用审计框架
BLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems
AI 导读
BLADE 是一个免训练框架，通过审计多智能体系统中决策对来源信息的使用方式，区分错误引入、传播与修复，从而定位责任智能体和关键错误步骤。在 Who&When 与 Who&When Pro 五个子集的 1228 条失败运行上，其步骤准确率在八种策略中达到最佳或并列最佳，较 All-at-once 高出 2.2-11.1 个百分点。
正文 · 原文
Abstract:Large language model multi-agent systems extend individual agents' capabilities through collaboration across specialized roles, tools, and workflows. Yet collaboration makes failures harder to diagnose: one agent may misinterpret a correct result while others carry the mistake forward. Failure attribution therefore seeks to identify the responsible agent and decisive error step. Recent methods trace dependencies, but knowing where information came from is not the same as knowing where it went wrong. We introduce BLADE (Blame Localization via Audited Dependency Evidence), a training-free framework that moves beyond tracing information to auditing its use. Using Jev for structured probabilistic judgments, BLADE uses dependency probabilities to select relevant source-decision handoffs for auditing. At these handoffs, it examines whether receiving decisions use their sources faithfully and within task requirements, distinguishing error introduction, propagation, and repair. These findings inform a global diagnosis that considers all execution steps. Without reference answers, BLADE achieves the best or tied-best step accuracy among eight strategies under a shared Jev decision interface on 1,228 failed runs across five Who&When and Who&When Pro subsets, outperforming All-at-once by 2.2-11.1 percentage points. Making responsibility evidence explicit offers a path toward more interpretable and reliable agentic systems.
| Comments: | 16 pages, 6 figures, 3 tables |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.18780 [cs.AI] |
| (or arXiv:2610.18780v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18780 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xiaoguang Guo [view email]
[v1]
Tue, 13 Oct 2026 17:34:34 UTC (592 KB)
来源：arXiv cs.AI · arxiv.org