Towards In-Depth Root Cause Localization for Microservices with Multi-Agent Recursion-of-Thought

TL;DR

This paper introduces RCLAgent, a multi-agent recursive reasoning framework that improves root cause localization in complex microservice systems by enhancing accuracy and efficiency through parallel, trace graph-based analysis.

Contribution

The paper proposes a novel multi-agent recursion-of-thought approach for microservice root cause localization, addressing limitations of context explosion and serial reasoning in existing LLM-based methods.

Findings

RCLAgent outperforms state-of-the-art methods in localization accuracy.

RCLAgent achieves higher inference efficiency.

Extensive experiments validate the effectiveness of RCLAgent.

Abstract

As modern microservice systems grow increasingly complex due to dynamic interactions and evolving runtime environments, they experience failures with rising frequency. Ensuring system reliability therefore critically depends on accurate root cause localization (RCL). While numerous traditional machine learning and deep learning approaches have been explored for this task, they often suffer from limited interpretability and poor transferability across deployments. More recently, large language model (LLM)-based methods have been proposed to address these issues. However, existing LLM-based approaches still face two fundamental limitations: context explosion, which dilutes critical evidence and degrades localization accuracy, and serial reasoning structures, which hinder deep causal exploration and impair inference efficiency. In this paper, we conduct a comprehensive study of both how human SREs perform root cause localization in practice and why existing LLM-based methods fall short. Motivated by these findings, we introduce RCLAgent, an in-depth root cause localization framework for microservice systems that realizes multi-agent recursion-of-thought with parallel reasoning. RCLAgent decomposes the diagnostic process along the trace graph by assigning each span to a Dedicated Agent and organizing agents recursively and in parallel according to the graph topology, with the final diagnosis obtained by synthesizing the Root-Level Diagnosis Report and the Global Evidence Graph. Extensive experiments on multiple public benchmarks demonstrate that RCLAgent consistently outperforms state-of-the-art methods in both localization accuracy and inference efficiency.