In cloud-scale systems, failures are the norm. A distributed computing cluster exhibits hundreds of machine failures and thousands of disk failures; software bugs and misconfigurations are reported to be more frequent. The demand for autonomous, AI-driven reliability engineering continues to grow, as existing humanin-the-loop practices can hardly keep up with the scale of modern clouds. This paper presents STRATUS, an LLM-based multi-agent system for realizing autonomous Site Reliability Engineering (SRE) of cloud services. STRATUS consists of multiple specialized agents (e.g., for failure detection, diagnosis, mitigation), organized in a state machine to assist system-level safety reasoning and enforcement. We formalize a key safety specification of agentic SRE systems like STRATUS, termed Transactional No-Regression (TNR), which enables safe exploration and iteration. We show that TNR can effectively improve autonomous failure mitigation. STRATUS significantly outperforms state-of-the-art SRE agents in terms of success rate of failure mitigation problems in AIOpsLab and ITBench (two SRE benchmark suites), by at least 1.5 times across various models. STRATUS shows a promising path toward practical deployment of agentic systems for cloud reliability.

翻译：在云计算规模的系统中，故障是常态。分布式计算集群会经历数百次机器故障和数千次磁盘故障；软件缺陷与配置错误的报告频率更高。随着现有的人工参与模式难以跟上现代云系统的规模，对自主化、人工智能驱动的可靠性工程需求持续增长。本文提出STRATUS——一种基于大语言模型的多智能体系统，用于实现云服务的自主站点可靠性工程（SRE）。STRATUS由多个专业化智能体（例如负责故障检测、诊断、缓解）组成，并按状态机机制组织以支持系统级安全推理与保障。我们形式化定义了STRATUS这类智能SRE系统的关键安全规范——即事务性无回归（TNR），该规范可实现安全探索与迭代。研究表明，TNR能够有效提升自主故障缓解能力。在AIOpsLab与ITBench（两个SRE基准测试套件）中，STRATUS在跨多种模型的故障缓解问题成功率上，相较当前最先进的SRE智能体显著提升至少1.5倍。STRATUS为在云可靠性领域实际部署智能体系统展示了可行路径。