Evaluating Agentic Configuration Repair for Computer Networks
For network operators, this work addresses the critical problem of misconfiguration-induced outages by evaluating LLM-based repair, though the gains are incremental.
The paper benchmarks LLMs augmented with formal verification and retrieval tools for automated network configuration repair, showing agentic architectures improve repair efficacy by 12% and safety by 17% over base LLMs.
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.