STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds
Abstract
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.
Cite
@article{arxiv.2506.02009,
title = {STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds},
author = {Yinfang Chen and Jiaqi Pan and Jackson Clark and Yiming Su and Noah Zheutlin and Bhavya Bhavya and Rohan Arora and Yu Deng and Saurabh Jha and Tianyin Xu},
journal= {arXiv preprint arXiv:2506.02009},
year = {2026}
}
Comments
10 pages for main text