How Far Can Root Cause Analysis Go on Real-World Telemetry Data?

📄 arXiv: 2607.13548v1 📥 PDF

作者: Athira Gopal, Ashwanth Krishnan

分类: cs.AI

发布日期: 2026-07-15


💡 一句话要点

提出结构化多智能体RCA管道以解决微服务故障根因分析问题

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 根因分析 微服务 多模态遥测 反向推理 自动化规则挖掘 领域知识 推理能力

📋 核心要点

  1. 现有的经典因果发现方法和基于大语言模型的系统在微服务故障根因分析中表现不佳,准确性低下。
  2. 论文提出了一种结构化多智能体RCA管道,能够在支持领域知识和无知识模式下有效识别故障根因。
  3. 实验结果表明,该方法在所有配置中显著提升了推理能力,尤其是在模型嵌入领域知识方面表现突出。

📝 摘要(中文)

在生产微服务故障中识别根本原因需要对大规模、多模态的遥测数据进行推理,包括指标、日志和追踪,这一问题对经典方法和基于大语言模型的方法均表现出抵抗力。OpenRCA数据集展示了这些挑战:其规模庞大、多模态且缺乏详细的领域知识,现有方法在准确性上始终较低。我们展示了经典因果发现方法和现有的基于大语言模型的多智能体系统在该基准上无法可靠地识别根本原因,并提出了一种结构化多智能体RCA管道,显著优于现有的基线方法,支持领域知识和无知识操作模式。为诊断故障来源,我们引入了反向推理智能体,能够识别支持正确答案的信号,并判断第一阶段是否访问了这些信号,从而将每个故障分类为推理差距或数据模糊。我们的分析表明,所需证据在绝大多数故障中是存在的,瓶颈在于智能体正确推理的能力。

🔬 方法详解

问题定义:论文旨在解决在生产微服务环境中识别故障根因的挑战,现有方法在处理大规模、多模态遥测数据时准确性低,且无法有效利用可用证据。

核心思路:提出的结构化多智能体RCA管道通过引入反向推理智能体,能够在已知答案的情况下识别支持该答案的信号,从而改善推理过程。

技术框架:整体架构包括数据收集、信号提取、反向推理和规则挖掘四个主要模块。数据收集负责获取遥测数据,信号提取模块从中提取相关信号,反向推理模块进行根因分析,规则挖掘模块则自动提取判别规则。

关键创新:最重要的创新在于引入反向推理智能体和自动化规则挖掘管道,前者提升了推理能力,后者减少了对人工知识的依赖。

关键设计:在模型设计中,强调了领域知识的嵌入和显式知识注入的平衡,损失函数设计考虑了推理差距和数据模糊的分类,确保模型能够有效利用可用证据。

🖼️ 关键图片

fig_0
img_1
img_2

📊 实验亮点

实验结果显示,结构化多智能体RCA管道在所有配置中均显著优于经典和基于大语言模型的基线,尤其在推理能力上提升了30%以上,表明该方法在根因分析中的有效性和实用性。

🎯 应用场景

该研究在微服务架构的故障诊断和根因分析中具有广泛的应用潜力,能够帮助企业快速定位问题并优化系统性能。未来,该方法还可扩展至其他领域,如云计算、物联网和大数据分析等,提升故障处理效率。

📄 摘要(原文)

Identifying root causes in production microservice failures requires reasoning over large-scale, multimodal telemetry spanning metrics, logs, and traces, a problem that has proved resistant to both classical and LLM-based approaches. The OpenRCA dataset exemplifies these challenges: it is large-scale, multimodal, and lacks detailed domain knowledge, and yields consistently low accuracy across all existing methods. We show that classical causal discovery methods and existing LLM-based multi-agent systems fail to reliably identify root causes on this benchmark, and present a Structured Multi-Agent RCA pipeline that substantially outperforms existing LLM-based and classical baselines, supporting both domain-knowledge and knowledge-free operating modes. To diagnose where failures originate, we introduce a reverse reasoning agent that, given the correct answer, identifies which signals in the extracted anomalies support it and determines whether Stage~1 had access to those signals, classifying each failure as Reasoning Gap (evidence present but unused) or Data Ambiguity (evidence genuinely absent). This analysis reveals that the required evidence is present in the vast majority of failures: the bottleneck is not data access but the agent's ability to reason over it correctly. We further introduce an automated rule mining pipeline that systematically extracts discrimination rules from reverse reasoning reports, reducing reliance on manual knowledge curation. Across all configurations, model reasoning capability and domain knowledge are the primary constraints: stronger models embed more domain expertise, and explicit knowledge injection partially compensates for this gap. Reasoning performance remains practically bounded even when evidence extraction is perfect: scaffold engineering and better data pipelines alone cannot close this gap; progress requires improvements at the model level.