E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-Tuning

TL;DR

This paper presents E2E-REME, an end-to-end reinforcement fine-tuned model for microservice auto-remediation, outperforming existing LLM-based approaches in accuracy and efficiency.

Contribution

It introduces a new task, E2E-MR, and a benchmark, MicroRemed, along with a novel auto-remediation model trained via experience-simulation reinforcement fine-tuning.

Findings

E2E-REME achieves higher accuracy than nine baseline LLMs.

E2E-REME demonstrates improved efficiency in microservice failure recovery.

The benchmark MicroRemed enables comprehensive evaluation of auto-remediation methods.

Abstract

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.