# SRE-Marathon: A Continuous, Change-Driven Benchmark for Autonomous Site Reliability Agents

arXiv: https://arxiv.org/abs/2609.33023 · HTML: https://mlsanity.com/paper/2609.33023/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 54 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 30 of 33)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2505.24760/) (2025)
- [Establishing Best Practices for Building Rigorous Agentic Benchmarks](https://mlsanity.com/paper/2507.02825/) (2025)
- [Automatic Root Cause Analysis via Large Language Models for Cloud Incidents](https://mlsanity.com/paper/2305.15778/) (2023)
- [Vending-Bench: A Benchmark for Long-Term Coherence of Autonomous Agents](https://mlsanity.com/paper/2502.15840/) (2025)
- [RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models](https://mlsanity.com/paper/2310.16340/) (2023)
- [Exploring LLM-based Agents for Root Cause Analysis](https://mlsanity.com/paper/2403.04123/) (2024)
- [ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks](https://mlsanity.com/paper/2502.05352/) (2025)
- [AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds](https://mlsanity.com/paper/2501.06706/) (2025)
- [Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis](https://mlsanity.com/paper/2502.08224/) (2025)
- [RCAEval: A Benchmark for Root Cause Analysis of Microservice Systems with Telemetry Data](https://mlsanity.com/paper/2412.17015/) (2024)
- [Xpert: Empowering Incident Management with Query Recommendations via Large Language Models](https://mlsanity.com/paper/2312.11988/) (2023)
- [STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Clouds](https://mlsanity.com/paper/2506.02009/) (2025)
- [A Survey of AIOps in the Era of Large Language Models](https://mlsanity.com/paper/2507.12472/) (2025)
- [Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems](https://mlsanity.com/paper/2603.00468/) (2026)
- [Nissist: An Incident Mitigation Copilot based on Troubleshooting Guides](https://mlsanity.com/paper/2402.17531/) (2024)
- [COCA: Generative Root Cause Analysis for Distributed Systems with Code Knowledge](https://mlsanity.com/paper/2503.23051/) (2025)
- [SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios](https://mlsanity.com/paper/2605.07161/) (2026)
- [OpsAgent: An Evolving Multi-agent System for Incident Management in Microservices](https://mlsanity.com/paper/2510.24145/) (2025)
- [StepFly: Agentic Troubleshooting Guide Automation for Incident Diagnosis](https://mlsanity.com/paper/2510.10074/) (2025)
- [OpenRCA 2.0: From Outcome Labels to Causal Process Supervision](https://mlsanity.com/paper/2606.27154/) (2026)
- [Knowledge-aware Alert Aggregation in Large-scale Cloud Systems: a Hybrid Approach](https://mlsanity.com/paper/2403.06485/) (2024)
- [ORCA-bench: How Ready Are Language Model Agents for Oncall?](https://mlsanity.com/paper/2607.28545/) (2026)
- [Agentic Observability: Automated Alert Triage for Adobe E-Commerce](https://mlsanity.com/paper/2602.02585/) (2026)

## Abstract (arXiv)

Benchmarks for site reliability engineering (SRE) agents are typically episodic: one fault is injected, the agent receives an incident task, and its response is scored. Production operation is not. Incidents surface through noisy alerts, overlap in time, and often originate from code or configuration changes. We present SRE-Marathon, a benchmark for long-horizon, continuous SRE operation. An agent is invoked at a fixed cadence with cumulative alert history and a persistent workspace while operating a live two-zone Kubernetes deployment as a fault orchestrator injects overlapping faults according to a seeded, production-calibrated schedule. Curated code and configuration changes deployed through the same build pipeline available for repair. Each run is recorded into a sealed bundle and scored offline: Marathon-Score credits each injected fault for ordered progress through correlation, localization, and repair, with all metrics computed deterministically from recorded system evidence. Across three applications and about sixty faults per run, the best of 10 methods reaches only 41.3 out of 100. Agents often correlate and localize faults, but almost never complete repairs while the faults remain active.