一句话：提出自演化多智能体系统 OpsAgent，通过免训练数据处理器与多智能体协作实现可解释、低成本、可泛化的微服务事件管理。
微服务系统的事件管理对可靠性至关重要，但人工检查指标、日志和追踪费力且易错；现有自动化方法难以跨系统泛化、可解释性有限且部署成本高。论文提出 OpsAgent：一个轻量、自演化的多智能体事件管理系统。它用免训练数据处理器将异构可观测数据转为结构化文本描述，并以多智能体协作框架使诊断推理透明、可审计；同时引入内部模型更新与外部经验积累相结合的双自演化机制，形成部署闭环。在 OPENRCA 基准上的实验表明其达到最先进性能，且可泛化、可解释、低成本并具自演化能力；在联想生产环境的部署验证了其工业有效性。
Incident management (IM) is central to the reliability of large-scale microservice systems. Yet manual IM, where on-call engineers examine metrics, logs, and traces is labor-intensive and error-prone in the face of massive and heterogeneous observability data. Existing automated IM approaches often struggle to generalize across systems, provide limited interpretability, and incur high deployment costs, which hinders adoption in practice. In this paper, we present OpsAgent, a lightweight, self-evolving multi-agent system for IM that employs a training-free data processor to convert heterogeneous observability data into structured textual descriptions, along with a multi-agent collaboration framework that makes diagnostic inference transparent and auditable. To support continual capability growth, OpsAgent also introduces a dual self-evolution mechanism that integrates internal model updates with external experience accumulation, thereby closing the deployment loop. Comprehensive experiments on the OPENRCA benchmark demonstrate state-of-the-art performance and show that OpsAgent is generalizable, interpretable, cost-efficient, and self-evolving, making it a practically deployable and sustainable solution for long-term operation in real-world microservice systems. Notably, its deployment in Lenovo’s production environment further validates its effectiveness in real-world industrial settings.
@inproceedings{paperbot12377,
title = {OpsAgent: An Evolving Multi-agent System for Incident Management in Microservices},
author = {Yu Luo and Jiamin Jiang and Jingfei Feng and Lei Tao and Qingliang Zhang and Xidao Wen and Yongqian Sun and Shenglin Zhang and Tong Liu and Wenjie Zhang and Dan Pei},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834479}
}