MicroRemed: Benchmarking LLMs in Microservices Remediation

TL;DR

MicroRemed introduces a benchmark for evaluating large language models in automatically generating system recovery scripts for microservices, highlighting current challenges and proposing a multi-agent reasoning framework to improve remediation performance.

Contribution

This paper presents the first benchmark for LLMs in microservice remediation and introduces ThinkRemed, a multi-agent framework that enhances reasoning capabilities.

Findings

Current LLMs struggle with microservice remediation tasks.

ThinkRemed improves remediation success through iterative reasoning.

Benchmark challenges highlight the need for advanced reasoning in LLMs.

Abstract

Large Language Models (LLMs) integrated with agent-based reasoning frameworks have recently shown strong potential for autonomous decision-making and system-level operations. One promising yet underexplored direction is microservice remediation, where the goal is to automatically recover faulty microservice systems. Existing approaches, however, still rely on human-crafted prompts from Site Reliability Engineers (SREs), with LLMs merely converting textual instructions into executable code. To advance research in this area, we introduce MicroRemed, the first benchmark for evaluating LLMs in end-to-end microservice remediation, where models must directly generate executable Ansible playbooks from diagnosis reports to restore system functionality. We further propose ThinkRemed, a multi-agent framework that emulates the reflective and perceptive reasoning of SREs. Experimental results show that MicroRemed presents substantial challenges to current LLMs, while ThinkRemed improves end-to-end remediation performance through iterative reasoning and system reflection. The benchmark is available at https://github.com/LLM4AIOps/MicroRemed.