NetIntent: Leveraging Large Language Models for End-to-End Intent-Based SDN Automation

TL;DR

This paper introduces NetIntent, a framework leveraging large language models to automate the entire Intent-Based Networking (IBN) process in SDN, supported by a new benchmarking suite for evaluating LLM performance in this domain.

Contribution

It presents NetIntent, a novel, adaptable framework for fully automating IBN lifecycle tasks using LLMs, and introduces IBNBench, a benchmarking suite with four datasets for evaluating LLMs in SDN intent translation and conflict detection.

Findings

LLMs show potential in isolated IBN tasks.

Benchmark results reveal wide performance variation among 33 LLMs.

NetIntent achieves consistent end-to-end IBN automation in SDN controllers.

Abstract

Intent-Based Networking (IBN) often leverages the programmability of Software-Defined Networking (SDN) to simplify network management. However, significant challenges remain in automating the entire pipeline, from user-specified high-level intents to device-specific low-level configurations. Existing solutions often rely on rigid, rule-based translators and fixed APIs, limiting extensibility and adaptability. By contrast, recent advances in large language models (LLMs) offer a promising pathway that leverages natural language understanding and flexible reasoning. However, it is unclear to what extent LLMs can perform IBN tasks. To address this, we introduce IBNBench, a first-of-its-kind benchmarking suite comprising four novel datasets: Intent2Flow-ODL, Intent2Flow-ONOS, FlowConflict-ODL, and FlowConflict-ONOS. These datasets are specifically designed for evaluating LLMs performance in intent translation and conflict detection tasks within the industry-grade SDN controllers ODL and ONOS. Our results provide the first comprehensive comparison of 33 open-source LLMs on IBNBench and related datasets, revealing a wide range of performance outcomes. However, while these results demonstrate the potential of LLMs for isolated IBN tasks, integrating LLMs into a fully autonomous IBN pipeline remains unexplored. Thus, our second contribution is NetIntent, a unified and adaptable framework that leverages LLMs to automate the full IBN lifecycle, including translation, activation, and assurance within SDN systems. NetIntent orchestrates both LLM and non-LLM agents, supporting dynamic re-prompting and contextual feedback to robustly execute user-defined intents with minimal human intervention. Our implementation of NetIntent across both ODL and ONOS SDN controllers achieves a consistent and adaptive end-to-end IBN realization.