LLM-Powered Agentic AI for 5G/6G Networks: A Tutorial and Survey on Architectures, Protocols, and Standardization
Networking and Internet ArchitectureArtificial Intelligence
Summary
The authors explain how new AI technologies, especially those using large language models, can make future telecom networks like 5G and 6G smarter and more independent in managing themselves. They note that past studies often looked at AI and networks separately, so the authors combine these fields to show how AI can actually control and improve network operations. Their work is split into two parts: the first introduces key concepts about network control and AI basics, while the second connects AI abilities to real-world telecom standards and projects. They also point out remaining challenges to making fully autonomous telecom systems.
Authors
Mazene Ameur, Abdelkader Mekrache, Bouziane Brik, Adlen Ksentini
Abstract
Agentic Artificial Intelligence (AI), enabled by Large Language Models, marks a shift from rule-based automation toward autonomous, goal-driven control of Next-Generation Networks (NGNs). Existing surveys treat the two domains in isolation, leaving protocol integration, evaluation, and standardization alignment underexplored. To address this gap, a two-part tutorial-and-survey is presented. Part I formalises the control, management, and AI-native planes of 5G and 6G. It then covers the foundations of agentic systems: reasoning, planning, tool use, multi-agent coordination, and evaluation. Part II maps agentic capabilities onto 5G/6G control surfaces, standardization, and major 6G initiatives. Finally, it identifies open challenges shaping autonomous telecommunications.