一句话：提出 TrioXpert，利用多模态数据与 LLM 协同推理实现微服务异常检测、故障分诊与根因定位。
微服务系统的自动化事件管理至关重要，但现有方法多依赖单模态数据，难以同时处理异常检测（AD）、故障分诊（FT）和根因定位（RCL），且推理证据不足、可解释性弱。本文提出 TrioXpert，一个端到端事件管理框架：针对不同模态设计三条独立数据处理流水线，从数值与文本维度刻画系统状态，并利用大语言模型协同推理同时完成多任务，输出清晰推理证据。在两个微服务数据集上，AD、FT、RCL 分别提升 4.7%–57.7%、2.1%–40.6%、1.6%–163.1%，并已在联想生产环境部署。
Automated incident management plays a pivotal role in large-scale microservice systems. However, many existing methods rely solely on single-modal data (e.g., metrics, logs, and traces) and struggle to simultaneously address multiple downstream tasks, including anomaly detection (AD), failure triage (FT), and root cause localization (RCL). Moreover, the lack of clear reasoning evidence in current techniques often leads to insufficient interpretability. To address these limitations, we propose TrioXpert, an end-to-end incident management framework capable of fully leveraging multimodal data. TrioXpert designs three independent data processing pipelines based on the inherent characteristics of different modalities, comprehensively characterizing the operational status of microservice systems from both numerical and textual dimensions. It employs a collaborative reasoning mechanism using large language models (LLMs) to simultaneously handle multiple tasks while providing clear reasoning evidence to ensure strong interpretability. We conducted extensive evaluations on two microservice system datasets, and the experimental results demonstrate that TrioXpert achieves outstanding performance in AD (improving by 4.7% to 57.7%), FT (improving by 2.1% to 40.6%), and RCL (improving by 1.6% to 163.1%) tasks. TrioXpert has also been deployed in Lenovo’s production environment, demonstrating substantial gains in diagnostic efficiency and accuracy.
DOI 原文 ·
@inproceedings{paperbot9208,
title = {TrioXpert: An Automated Incident Management Framework for Microservice System},
author = {Yongqian Sun and Yu Luo and Xidao Wen and Yuan Yuan and Xiaohui Nie and Shenglin Zhang and Tong Liu and Xi Luo},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00267}
}