MicroRemed: Benchmarking LLMs in Microservices Remediation
This addresses the need for autonomous recovery in microservice systems, offering a new benchmark and framework for AIOps, though it is incremental in advancing existing agent-based methods.
The paper tackles the problem of automating microservice remediation by introducing MicroRemed, the first benchmark for evaluating LLMs in generating executable Ansible playbooks from diagnosis reports, and shows that ThinkRemed, a multi-agent framework, improves end-to-end performance through iterative reasoning.
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.