用智能流程自动诊断云服务故障根源，准确率提升6.3倍。
PRAXIS: Integrating Program Analysis with Observability for Root-Cause Analysis
- 结合服务依赖与代码依赖图，用大模型结构化遍历定位问题
- 相比现有方法，故障定位准确率最高提升6.3倍，耗 token 减少5.3倍
- 适合运维团队和云平台研发人员快速排查复杂生产故障
未解决的生产环境云故障平均每小时造成超200万美元损失。本文提出PRAXIS，一个用于诊断由代码或配置引发的云故障的智能工作流编排器。PRAXIS通过大语言模型驱动，对两类图进行结构化遍历：（1）服务依赖图（SDG），刻画微服务间的依赖关系；（2）哈姆洛克块程序依赖图（PDG），捕捉每个微服务的代码级依赖。相较于最先进的ReAct基线方法，PRAXIS在故障根因分析（RCA）准确率上最高提升6.3倍，同时将令牌消耗降低5.3倍。该系统已在一组包含30个真实世界故障的案例集上验证，并正在整理为RCA基准数据集。
原文摘要 · Abstract (English)
Unresolved production cloud incidents cost an average of over $2M per hour. This paper introduces PRAXIS, an orchestrator that manages and deploys an agentic workflow for diagnosing code- and configuration-caused cloud incidents. PRAXIS employs an LLM-driven structured traversal over two types of graph: (1) a service dependency graph (SDG) that captures microservice-level dependencies; and (2) a hammock-block program dependence graph (PDG) that captures code-level dependencies for each microservice. Compared to state-of-the-art ReAct baselines, PRAXIS improves RCA accuracy by up to 6.3x while reducing token consumption by 5.3x. PRAXIS is demonstrated on a set of 30 comprehensive real-world incidents that is being compiled into an RCA benchmark.
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。