INTA: Intent-Based Translation for Network Configuration with LLM Agents

TL;DR

INTA is an intent-based framework utilizing LLMs to automate and improve the accuracy of translating network device configurations across different models, enhancing network management efficiency.

Contribution

The paper introduces INTA, a novel LLM-based intent-driven approach for network configuration translation, addressing complexity and improving accuracy over existing methods.

Findings

Achieves 98.15% translation accuracy in syntax and view correctness.

Reaches 84.72% command recall rate for target configurations.

Demonstrates strong generalizability on real-world datasets.

Abstract

Translating configurations between different network devices is a common yet challenging task in modern network operations. This challenge arises in typical scenarios such as replacing obsolete hardware and adapting configurations to emerging paradigms like Software Defined Networking (SDN) and Network Function Virtualization (NFV). Engineers need to thoroughly understand both source and target configuration models, which requires considerable effort due to the complexity and evolving nature of these specifications. To promote automation in network configuration translation, we propose INTA, an intent-based translation framework that leverages Large Language Model (LLM) agents. The key idea of INTA is to use configuration intent as an intermediate representation for translation. It first employs LLMs to decompose configuration files and extract fine-grained intents for each configuration fragment. These intents are then used to retrieve relevant manuals of the target device. Guided by a syntax checker, INTA incrementally generates target configurations. The translated configurations are further verified and refined for semantic consistency. We implement INTA and evaluate it on real-world configuration datasets from the industry. Our approach outperforms state-of-the-art methods in translation accuracy and exhibits strong generalizability. INTA achieves an accuracy of 98.15% in terms of both syntactic and view correctness, and a command recall rate of 84.72% for the target configuration. The semantic consistency report of the translated configuration further demonstrates its practical value in real-world network operations.