STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915873080475648 |
|---|---|
| author | Chen, Yinfang Pan, Jiaqi Clark, Jackson Su, Yiming Zheutlin, Noah Bhavya, Bhavya Arora, Rohan Deng, Yu Jha, Saurabh Xu, Tianyin |
| author_facet | Chen, Yinfang Pan, Jiaqi Clark, Jackson Su, Yiming Zheutlin, Noah Bhavya, Bhavya Arora, Rohan Deng, Yu Jha, Saurabh Xu, Tianyin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02009 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds Chen, Yinfang Pan, Jiaqi Clark, Jackson Su, Yiming Zheutlin, Noah Bhavya, Bhavya Arora, Rohan Deng, Yu Jha, Saurabh Xu, Tianyin Distributed, Parallel, and Cluster Computing 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. |
| title | STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2506.02009 |