通过因果图追溯故障源头，快速定位多智能体系统错误根源。
AgentTrace: Causal Graph Tracing for Root Cause Analysis in Deployed Multi-Agent Systems
- 从执行日志重建因果图，反向追踪错误传播路径。
- 在多种真实场景中准确定位故障，响应时间低于1秒。
- 无需大模型推理，适合生产环境实时诊断。
随着多智能体AI系统在现实场景中的广泛应用——从自动客服到DevOps修复——故障诊断因级联效应、隐藏依赖和长执行日志而日益困难。我们提出AgentTrace，一种轻量级的后验故障诊断框架，用于部署后的多智能体工作流。AgentTrace从执行日志重构因果图，从错误表现反向追溯，并利用可解释的结构与位置信号对候选根因进行排序，且调试时无需大语言模型（LLM）推理。在涵盖常见部署模式的多样化多智能体故障基准测试中，AgentTrace以高精度和亚秒级延迟定位根因，显著优于基于启发式和基于大模型的基线方法。结果表明，因果追溯为提升智能体系统在实际应用中的可靠性与可信度提供了实用基础。
原文摘要 · Abstract (English)
As multi-agent AI systems are increasingly deployed in real-world settings - from automated customer support to DevOps remediation - failures become harder to diagnose due to cascading effects, hidden dependencies, and long execution traces. We present AgentTrace, a lightweight causal tracing framework for post-hoc failure diagnosis in deployed multi-agent workflows. AgentTrace reconstructs causal graphs from execution logs, traces backward from error manifestations, and ranks candidate root causes using interpretable structural and positional signals - without requiring LLM inference at debugging time. Across a diverse benchmark of multi-agent failure scenarios designed to reflect common deployment patterns, AgentTrace localizes root causes with high accuracy and sub-second latency, significantly outperforming both heuristic and LLM-based baselines. Our results suggest that causal tracing provides a practical foundation for improving the reliability and trustworthiness of agentic systems in the wild.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。