From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications

TL;DR

The paper addresses the need for intelligent, adaptive 6G networks by surveying the progression from Large AI Models (LAMs) to Agentic AI. It offers a structured taxonomy of core components (Transformers, ViT, VAE, Diffusion, DiT, MoE) and model classes (LLM, LVM, LMM, LRM, lightweight LAM), and proposes a LAM-centric design paradigm for communications, including data pipelines, internal/external learning (pre-training, fine-tuning, alignment, RAG, KG). It then formulates an Agentic AI framework for intelligent communications, detailing system architecture (LAMs, planners, knowledge bases, tools, memory), single- and multi-agent interactions, and a multi-agent data-retrieval/planning/evaluation loop. The tutorial also surveys application domains (semantic/IoT/edge/network/security/UAV) and outlines research challenges and future directions, aiming to guide efficient, secure, and scalable next-generation intelligent communication systems. Overall, the work provides a comprehensive reference for researchers and practitioners seeking to evolve from model-driven to agent-driven intelligent communications in 6G contexts.

Abstract

With the advent of 6G communications, intelligent communication systems face multiple challenges, including constrained perception and response capabilities, limited scalability, and low adaptability in dynamic environments. This tutorial provides a systematic introduction to the principles, design, and applications of Large Artificial Intelligence Models (LAMs) and Agentic AI technologies in intelligent communication systems, aiming to offer researchers a comprehensive overview of cutting-edge technologies and practical guidance. First, we outline the background of 6G communications, review the technological evolution from LAMs to Agentic AI, and clarify the tutorial's motivation and main contributions. Subsequently, we present a comprehensive review of the key components required for constructing LAMs. We further categorize LAMs and analyze their applicability, covering Large Language Models (LLMs), Large Vision Models (LVMs), Large Multimodal Models (LMMs), Large Reasoning Models (LRMs), and lightweight LAMs. Next, we propose a LAM-centric design paradigm tailored for communications, encompassing dataset construction and both internal and external learning approaches. Building upon this, we develop an LAM-based Agentic AI system for intelligent communications, clarifying its core components such as planners, knowledge bases, tools, and memory modules, as well as its interaction mechanisms. We also introduce a multi-agent framework with data retrieval, collaborative planning, and reflective evaluation for 6G. Subsequently, we provide a detailed overview of the applications of LAMs and Agentic AI in communication scenarios. Finally, we summarize the research challenges and future directions in current studies, aiming to support the development of efficient, secure, and sustainable next-generation intelligent communication systems.

Figures (7)

• Figure 1: LAMs and Agentic AI empowered 6G.
• Figure 2: Overall organization of the tutorial.
• Figure 3: The structured design pipeline of LAMs for communications through various learning methods.
• Figure 4: The architecture of the LAM-based Agentic AI system.
• Figure 5: Schematic diagram of CommLLM jiang2024large3.