# STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds

arXiv: https://arxiv.org/abs/2506.02009 · HTML: https://mlsanity.com/paper/2506.02009/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2025.

## Built on by (most cited first, 19 of 19)

- [SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios](https://mlsanity.com/paper/2605.07161/) (2026)
- [Agentic Services Computing](https://mlsanity.com/paper/2509.24380/) (2025)
- [OpenRCA 2.0: From Outcome Labels to Causal Process Supervision](https://mlsanity.com/paper/2606.27154/) (2026)
- [Graph-Free Root Cause Analysis](https://mlsanity.com/paper/2601.21359/) (2026)
- [Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagation](https://mlsanity.com/paper/2601.17915/) (2026)
- [PRAXIS: Integrating Program Analysis with Observability for Root-Cause Analysis](https://mlsanity.com/paper/2512.22113/) (2025)
- [Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations](https://mlsanity.com/paper/2604.26805/) (2026)
- [AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis](https://mlsanity.com/paper/2603.03378/) (2026)
- [Rebooting Microreboot: Architectural Support for Safe, Parallel Recovery in Microservice Systems](https://mlsanity.com/paper/2604.09963/) (2026)
- [From Natural Language to PromQL: A Catalog-Driven Framework with Dynamic Temporal Resolution for Cloud-Native Observability](https://mlsanity.com/paper/2604.13048/) (2026)
- [Auditable Graph-Guided Root Cause Analysis for Kubernetes Incidents](https://mlsanity.com/paper/2606.08590/) (2026)
- [A Dual-Track Framework for Template-Constrained LaTeX Conversion](https://mlsanity.com/paper/2606.23107/) (2026)
- [KRCA: An Efficient Root Cause Analysis System in Hyper-scale Microservice Systems via Agentic AI](https://mlsanity.com/paper/2607.01788/) (2026)
- [Towards a Systems Foundation for Agentic Cloud Management](https://mlsanity.com/paper/2607.25883/) (2026)
- [Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysis](https://mlsanity.com/paper/2608.21310/) (2026)
- [ASTRA - Agentic System for Ticket Resolution and Analysis](https://mlsanity.com/paper/2608.28790/) (2026)
- [SRE-Marathon: A Continuous, Change-Driven Benchmark for Autonomous Site Reliability Agents](https://mlsanity.com/paper/2609.33023/) (2026)
- [Reliability Engineering for AI Systems: Challenges, Methods, and Directions](https://mlsanity.com/paper/2609.35316/) (2026)
- [A Self-Defining Operator for Distributed Applications](https://mlsanity.com/paper/2610.14547/) (2026)

## Abstract (arXiv)

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.