Evaluating Agentic Configuration Repair for Computer Networks

Rufat Asadli, Benjamin Hoffman, Ioannis Protogeros, Laurent Vanbever

Keywords: llm, agents, safety, computer networks, configuration repair

TL;DR: An agentic setup with dynamic context retrieval, iterative search/replace editing, and verifier feedback improves computer network configuration repair over monolithic prompting by 12% efficacy and 17% safety regressions across open/closed models.

Abstract: Misconfigurations in computer networks remain a major source of critical Internet outages. Research is turning to Large Language Models (LLMs) to automate the complex, error-prone task of network configuration. However, even state-of-the-art models fail to resolve misconfigurations in large-scale, complex scenarios and often introduce new errors. In this work, we benchmark open- and closed-source LLMs augmented with formal network verification and context retrieval tools. We demonstrate that agentic architectures outperform base LLMs in repair efficacy (by 12% on average) and safety (by 17% on average), enabled by the ability to dynamically manage context and iteratively validate configuration repairs.

Track: Short Paper (4 pages)

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 46