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

2025-07-18

AI Summary

Existing rule-based or fixed-API Intent-Based Networking (IBN) systems suffer from limited scalability and adaptability. Method: We propose NetIntent, an end-to-end LLM-driven intent-driven SDN automation framework that integrates large language models (LLMs), natural language understanding, dynamic re-prompting, and ODL/ONOS controllers within a hybrid architecture combining LLM and non-LLM agents. We further introduce IBNBench—the first benchmark suite tailored for IBN tasks. Contribution/Results: Evaluated across 33 open-source LLMs, NetIntent significantly improves accuracy and robustness in translating high-level intents into low-level network configurations. It enables stable, scalable, and closed-loop configuration generation, activation, and assurance on both ODL and ONOS platforms. NetIntent constitutes the first unified IBN framework supporting dynamic contextual feedback and continuous evolution.

Technology Category

• Natural Language Processing: (Large) Language Models
• Intelligent Robots: Embodied AI
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Automating intent-based SDN from high-level intents to low-level configurations
• Evaluating LLMs for intent translation and conflict detection in SDN
• Integrating LLMs into a fully autonomous intent-based networking pipeline

Innovation

• Leverages LLMs for end-to-end SDN automation
• Introduces IBNBench for LLM performance evaluation
• Orchestrates LLM and non-LLM agents dynamically