From Observability Data to Diagnosis: An Evolving Multi-agent System for Incident Management in Cloud Systems
This addresses the labor-intensive and error-prone nature of manual incident management for cloud system engineers, offering a practical and sustainable automated solution.
The paper tackles the problem of automating incident management in cloud systems by introducing OpsAgent, a multi-agent system that converts observability data into structured descriptions and provides transparent diagnostic inference, achieving state-of-the-art performance on the OPENRCA benchmark with demonstrated generalizability, interpretability, cost-efficiency, and self-evolution.
Incident management (IM) is central to the reliability of large-scale cloud 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 cloud systems.