AISep 19, 2025

MicroRCA-Agent: Microservice Root Cause Analysis Method Based on Large Language Model Agents

arXiv:2509.15635v15 citationsh-index: 3Has Code
Originality Incremental advance
AI Analysis

This addresses fault localization in microservices, which is critical for system reliability, but appears incremental as it combines existing techniques like Drain parsing and Isolation Forest with LLMs.

The paper tackles microservice root cause analysis by proposing MicroRCA-Agent, a method using large language model agents with multimodal data fusion, achieving a final score of 50.71 in complex fault scenarios.

This paper presents MicroRCA-Agent, an innovative solution for microservice root cause analysis based on large language model agents, which constructs an intelligent fault root cause localization system with multimodal data fusion. The technical innovations are embodied in three key aspects: First, we combine the pre-trained Drain log parsing algorithm with multi-level data filtering mechanism to efficiently compress massive logs into high-quality fault features. Second, we employ a dual anomaly detection approach that integrates Isolation Forest unsupervised learning algorithms with status code validation to achieve comprehensive trace anomaly identification. Third, we design a statistical symmetry ratio filtering mechanism coupled with a two-stage LLM analysis strategy to enable full-stack phenomenon summarization across node-service-pod hierarchies. The multimodal root cause analysis module leverages carefully designed cross-modal prompts to deeply integrate multimodal anomaly information, fully exploiting the cross-modal understanding and logical reasoning capabilities of large language models to generate structured analysis results encompassing fault components, root cause descriptions, and reasoning trace. Comprehensive ablation studies validate the complementary value of each modal data and the effectiveness of the system architecture. The proposed solution demonstrates superior performance in complex microservice fault scenarios, achieving a final score of 50.71. The code has been released at: https://github.com/tangpan360/MicroRCA-Agent.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes