Large Language Models in Intent-Based Networking: a Comprehensive Survey Across the Intent Lifecycle
Marwa Tageldien, Bassant Selim, Lokman Sboui · 2025
The rising complexity of modern networks, particularly in 6 G environments, demands scalable and autonomous management frameworks. Intent-Based Networking (IBN) addresses this challenge by enabling users to specify high-level operational goals rather than low-level configurations. However, traditional IBN approaches remain limited by their reliance on strict intent interpretation mechanisms. Large Language Models (LLMs), with their advanced semantic understanding and contextual reasoning capabilities, can offer a promising enhancement to the IBN lifecycle. Hence, in this survey, we present the first dedicated and structured analysis of how LLMs are being integrated into the IBN paradigm. We examine the most recent literature to trace the application of LLMs across all five phases of the IBN lifecycle: intent profiling, translation, conflict resolution, policy activation, and assurance. Unlike prior works that treat LLMs and network management in isolation, this survey emphasizes their convergence, detailing how LLMs support context-aware interpretation, flexible policy generation, and dynamic adaptation in response to network variability. Additionally, we present a comprehensive taxonomy that maps current research efforts of LLM to IBN phases and the specific LLM models used in each phase. Furthermore, the survey offers an analysis of the limitations and open challenges associated with deploying LLMs into IBN systems.