Evaluating Agentic Configuration Repair for Computer Networks

2026-06-04

AI Summary

This study addresses the critical challenge of network outages caused by misconfigurations in large-scale networks, where existing large language models (LLMs) exhibit limited repair capabilities and often introduce new errors. To overcome these limitations, this work proposes an agent-based architecture that integrates formal verification with contextual retrieval to dynamically manage configuration context and iteratively validate repair proposals. As the first systematic evaluation of LLM agents for network configuration repair, the experimental results demonstrate that the proposed approach significantly outperforms baseline methods on both open-source and closed-source LLMs, achieving a 12% average improvement in repair success rate and a 17% increase in safety, effectively resolving original misconfigurations while preventing the introduction of new faults.

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.

Problem

• network misconfiguration
• Large Language Models
• configuration repair
• Internet outages
• agentic architectures

Innovation

• Agentic Architecture
• Network Configuration Repair
• Large Language Models
• Formal Verification
• Context Retrieval