Agentic Structured Graph Traversal for Root Cause Analysis of Code-related Incidents in Cloud Applications
This addresses the operational challenge of costly cloud incidents for cloud operators, though it is an incremental improvement over existing methods like ReAct.
The paper tackles the problem of diagnosing code- and configuration-related cloud incidents, which are costly and common, by introducing PRAXIS, an orchestrator that uses an LLM-driven structured traversal over service and code dependency graphs. It improves root cause analysis accuracy by up to 3.1x and reduces token consumption by 3.8x compared to state-of-the-art baselines.
Cloud incidents pose major operational challenges in production, with unresolved production cloud incidents cost on average over $2M per hour. Prior research identifies code- and configuration-related issues as the predominant category of root causes in cloud incidents. 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. Together, these graphs encode microservice- and code-level dependencies and the LLM acts as a traversal policy over these graphs, moving between services and code dependencies to localize and explain failures. Compared to state-of-the-art ReAct baselines, PRAXIS improves RCA accuracy by up to 3.1x while reducing token consumption by 3.8x. PRAXIS is demonstrated on a set of 30 comprehensive real-world incidents that is being compiled into an RCA benchmark.