LLM-Enhanced Failure Localization in Microservices: Integrating Multi-Modal Data and Expert Interpretation
- 20 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 19 (3) , 2275-2288
Abstract
Failure localization in microservice environments is increasingly challenging. While large language models (LLMs) have shown promise in software engineering tasks, existing approaches struggle to effectively integrate multi-modal telemetry data (e.g., log, metric and trace) and provide interpretable results. This paper presents LocaleXpert, a novel failure localization system that combines specialized LLM-based agents with traditional AIOps methods to diagnose issues in microservice environments. LocaleXpert introduces three key innovations: (1) a modular pipeline that transforms metrics, logs, and traces into natural language descriptions that LLMs can effectively process, (2) specialized expert agents that analyze each data type and collaborate to identify root causes, and (3) an interpretation mechanism that produces clear, actionable explanations of its reasoning process. Evaluation results show that LocaleXpert significantly outperforming baseline approaches in both accuracy and interpretability. The system has been successfully deployed in Microsoft's AIOpsLab benchmark, demonstrating its effectiveness.Keywords
Funding Information
- National Natural Science Foundation of China (62272249)
- National Natural Science Foundation of China (62302244)
- Fundamental Research Funds for the Central Universities (XXX-63253249)
This publication has 35 references indexed in Scilit:
- The rise and potential of large language model based agents: a surveyScience China Information Sciences, 2025
- SciAgents: Automating Scientific Discovery Through Bioinspired Multi‐Agent Intelligent Graph ReasoningAdvanced Materials, 2024
- ProtAgents: protein discovery via large language model multi-agent collaborations combining physics and machine learningDigital Discovery, 2024
- Eadro: An End-to-End Troubleshooting Framework for Microservices on Multi-source Data2023
- Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Models2023
- MicroSketch: Lightweight and Adaptive Sketch Based Performance Issue Detection and Localization in Microservice Systems2022
- Localization of Operational Faults in Cloud Applications by Mining Causal Dependencies in Logs Using Golden Signals2021
- MicroHECL: High-Efficient Root Cause Localization in Large-Scale Microservice Systems2021
- CloudRanger: Root Cause Identification for Cloud Native Systems2018
- FChain: Toward Black-Box Online Fault Localization for Cloud Systems2013