Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.24145 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918497592803328 |
|---|---|
| author | Luo, Yu Jiang, Jiamin Feng, Jingfei Tao, Lei Zhang, Qingliang Wen, Xidao Sun, Yongqian Zhang, Shenglin Pei, Dan |
| author_facet | Luo, Yu Jiang, Jiamin Feng, Jingfei Tao, Lei Zhang, Qingliang Wen, Xidao Sun, Yongqian Zhang, Shenglin Pei, Dan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_24145 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OpsAgent: An Evolving Multi-agent System for Incident Management in Microservices Luo, Yu Jiang, Jiamin Feng, Jingfei Tao, Lei Zhang, Qingliang Wen, Xidao Sun, Yongqian Zhang, Shenglin Pei, Dan Artificial Intelligence 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. |
| title | OpsAgent: An Evolving Multi-agent System for Incident Management in Microservices |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.24145 |