用强化学习训练模型，直接从故障报告生成修复脚本。
E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-Tuning
- 通过仿真经验强化学习训练模型，实现从诊断报告到修复脚本的端到端生成。
- 在真实平台测试中，修复准确率超9个主流大模型，平均耗时降低40%。
- 适合运维自动化、DevOps工程师及微服务系统可靠性研究者。
当前微服务系统规模与复杂度持续增长，导致故障频发且修复成本高昂。尽管已有基于大语言模型（LLM）的自动修复方法，但它们主要将文本指令转化为可执行的Ansible剧本，依赖专家设计的提示词，缺乏运行时知识引导，并依赖大规模通用LLM，限制了准确性与效率。本文提出端到端微服务修复（E2E-MR）新任务，要求直接从诊断报告生成可执行剧本以自主恢复故障系统。为支持严格评估，构建了MicroRemed基准，自动化完成微服务部署、故障注入、剧本执行与修复后验证。进一步提出E2E-REME模型，通过经验-仿真强化微调进行训练。在公开及工业级微服务平台上，与九种代表性LLM对比实验表明，E2E-REME在修复准确率和效率方面均表现更优。
原文摘要 · Abstract (English)
Contemporary microservice systems continue to grow in scale and complexity, leading to increasingly frequent and costly failures. While recent LLM-based auto-remediation approaches have emerged, they primarily translate textual instructions into executable Ansible playbooks and rely on expert-crafted prompts, lacking runtime knowledge guidance and depending on large-scale general-purpose LLMs, which limits their accuracy and efficiency. We introduce \textit{End-to-End Microservice Remediation} (E2E-MR), a new task that requires directly generating executable playbooks from diagnosis reports to autonomously restore faulty systems. To enable rigorous evaluation, we build \textit{MicroRemed}, a benchmark that automates microservice deployment, failure injection, playbook execution, and post-repair verification. We further propose \textit{E2E-REME}, an end-to-end auto-remediation model trained via experience-simulation reinforcement fine-tuning. Experiments on public and industrial microservice platforms, compared with nine representative LLMs, show that E2E-REME achieves superior accuracy and efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。