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 cuttingedge 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, including Transformers, Vision Transformers (ViTs), Variational AutoEncoders (VAEs), diffusion models, Diffusion Transformers (DiTs), and Mixture of Experts (MoEs). 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, including both single-agent and multi-agent interactions. 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.
- From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications
- Abstract
- Contents
- I. INTRODUCTION
- II. KEY CONCEPTS
- III. HOW TO DESIGN LARGE AI MODELS FOR COMMUNICATIONS
- IV. HOW TO DESIGN AGENTIC AI SYSTEMS FOR COMMUNICATIONS
- V. HOW TO OPTIMIZE COMMUNICATION SYSTEMS USING LAMS AND AGENTIC AI
- VI. RESEARCH CHALLENGES AND FUTURE DIRECTIONS
- VII. CONCLUSION
- The Team
- Contact Information for Source Code Submission or Update
- Update log
- Citation
Fig. 1: LAMs and Agentic AI empowered 6G.
Fig. 2: Overall organization of the tutorial.
Fig. 3: The structured design pipeline of LAMs for communications.
Fig. 4: The architecture of the LAM-based Agentic AI system.
Fig. 5: Schematic diagram of CommLLM
Fig. 6: The application scenarios of LAMs.
Fig. 7: The application scenarios of Agentic AI.
| Title | Release Time | Link | Download |
|---|---|---|---|
| AgentGPT | 2023 | Code | |
| Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions | 2023 | Paper | Code |
| OpenAgents: An Open Platform for Language Agent in The Wild | 2023 | Paper | Code |
| HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face | 2023 | Paper | Code |
| Dify | 2024 | Code | |
| AgentGym: Evolving Large Language Model-based Agents across Diverse Environments | 2024 | Paper | Code |
| PEER: Expertizing Domain-Specific Tasks with a Multi-Agent Framework and Tuning Methods | 2024 | Paper | Code |
| BabyAGI | 2025 | Code | |
| OpenManus | 2025 | Code | |
| AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents | 2025 | Paper | Code |
| LAM Category | Specific Models | model | Release Time | Link | Download |
|---|---|---|---|---|---|
| Large Language Model | GPT series | GPT-1 | 2020 | Paper | Code |
| GPT-2 | 2023 | Paper | Code | ||
| GPT-3 | 2023 | Paper | |||
| GPT-4 | 2023 | Paper | |||
| OpenAI o1 | 2024 | Paper | Code | ||
| Gemma series | Gemma 1 | 2024 | Paper | ||
| Gemma 2 | 2024 | Paper | |||
| LLaMA series | LLaMA-1 | 2023 | Paper | Code | |
| LLaMA-2 | 2023 | Paper | Code | ||
| LLaMA-3 | 2024 | Paper | Code | ||
| Large Vision Model | SAM series | SAM-1 | 2023 | Paper | Code |
| SAM-2 | 2024 | Paper | Code | ||
| DINO series | DINO V1 | 2021 | Paper | Code | |
| DINO V2 | 2023 | Paper | Code | ||
| Stable Diffusion series | Stable Diffusion V1 | 2022 | Paper | Code | |
| Stable Diffusion V2 | 2022 | Paper | Code | ||
| Stable Diffusion V3 | 2024 | Paper | |||
| Vision Language Model | LLaVA | LLaVA | 2024 | Paper | Code |
| Qwen-VL | Qwen-VL | 2023 | Paper | Code | |
| Qwen-VL-Chat | 2023 | Paper | Code | ||
| Mini-GPT4 | Mini-GPT4 | 2023 | Paper | Code | |
| Large Multimodal Model | CoDi series | CoDi-1 | 2024 | Paper | Code |
| CoDi-2 | 2024 | Paper | Code | ||
| Meta-Transformer | Meta-Transformer | 2023 | Paper | Code | |
| ImageBind | ImageBind | 2023 | Paper | Code | |
| World Model | Sora | Sora | 2024 | Paper | |
| JEPA | JEPA | 2022 | Paper | ||
| Vista | Vista | 2024 | Paper | Code | |
| Lightweight Large AI Model | TinyLlama | TinyLlama | 2024 | Paper | Code |
| MobileVLM | MobileVLM | 2024 | Paper | Code | |
| Mini-Gemini | Mini-Gemini | 2024 | Paper | Code | |
| Large Reasoning Model | |||||
| OpenAI o3-mini | OpenAI o3-mini | 2025 | Paper | ||
| DeepSeek | DeepSeek-R1 | 2025 | Paper | Code | |
| Qwen | Qwen-QwQ | 2025 | Paper | Code |
| Title | Release Time | Link | Download |
|---|---|---|---|
| ReAct: Synergizing Reasoning and Acting in Language Models | 2022 | Paper | Code |
| Least-to-Most Prompting Enables Complex Reasoning in Large Language Models | 2022 | Paper | |
| Tree of Thoughts: Deliberate Problem Solving with Large Language Models | 2023 | Paper | Code |
| Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models | 2023 | Paper | Code |
| Thought Graph: Generating Thought Process for Biological Reasoning | 2024 | Paper | Code |
| From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis | 2024 | Paper | Code |
| Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models | 2024 | Paper | Code |
| Step-by-Step Reasoning to Solve Grid Puzzles: Where do LLMs Falter? | 2024 | Paper | Code |
| Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs | 2024 | Paper | Code |
| Graph of thoughts: Solving elaborate problems with large language models | 2024 | Paper | Code |
| Generating SPARQL from Natural Language Using Chain-of-Thoughts Prompting | 2025 | Paper | Code |
| Understanding Before Reasoning: Enhancing Chain-of-Thought with Iterative Summarization Pre-Prompting | 2025 | Paper | Code |
| Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs | 2025 | Paper | Code |
| Enhancing LLM-Based Agents via Global Planning and Hierarchical Execution | 2025 | Paper | Code |
| Compositional Chain-of-Thought Prompting for Large Multimodal Models | 2025 | Paper | Code |
| Title | Release Time | Link | Download |
|---|---|---|---|
| Retrieval-augmented generation for large language models: A survey | 2023 | Paper | Code |
| HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models | 2024 | Paper | Code |
| RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing | 2024 | Paper | Code |
| Emerging trends: a gentle introduction to RAG | 2024 | Paper | Code |
| The Power of Noise: Redefining Retrieval for RAG Systems | 2024 | Paper | Code |
| MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries | 2024 | Paper | Code |
| HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation | 2025 | Paper | Code |
| Structured Review on RAG- and Multi-Agent Frameworks – Part II: Application-Based Assessment | 2025 | Paper | Code |
| HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation | 2025 | Paper | Code |
| Title | Release Time | Link | Download |
|---|---|---|---|
| Memory gym: Partially observable challenges to memory-based agents | 2023 | Paper | Code |
| A Survey on the Memory Mechanism of Large Language Model based Agents | 2024 | Paper | Code |
| xlstm: Extended long short-term memory | 2024 | Paper | Code |
| HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models | 2024 | Paper | Code |
| Persistent activity during working memory maintenance predicts long-term memory formation in the human hippocampus | 2024 | Paper | Code |
| SURVEYFORGE: On the Outline Heuristics, Memory-Driven Generation,and Multi-dimensional Evaluation for Automated Survey Writing | 2025 | Paper | Code |
| Advances and challenges in foundation agents: From brain-inspired intelligence to evolutionary, collaborative, and safe systems | 2025 | Paper | Code |
| A-mem: Agentic memory for llm agents | 2025 | Paper | Code |
| Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory | 2025 | Paper | Code |
| Title | Release Time | Link | Download |
|---|---|---|---|
| CodeTF: One-stop Transformer Library for State-of-the-art Code LLM | 2023 | Paper | Code |
| DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence | 2024 | Paper | Code |
| Lemur: Harmonizing Natural Language and Code for Language Agents | 2024 | Paper | Code |
| HDDLGym: A Tool for Studying Multi-Agent Hierarchical Problems Defined in HDDL with OpenAI Gym | 2025 | Paper | Code |
| OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models | 2025 | Paper | Code |
| The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search | 2025 | Paper | Code |
| Title | Release Time | Link | Download |
|---|---|---|---|
| Openagents: An open platform for language agents in the wild | 2023 | Paper | |
| Reflexion: Language agents with verbal reinforcement learning | 2023 | Paper | Code |
| Large language model enhanced multi-agent systems for 6g communications | 2024 | Paper | Code |
| Generative ai agents with large language model for satellite networks via a mixture of experts transmission | 2024 | Paper | Code |
| Cached model-as-a-resource: Provisioning large language model agents for edge intelligence in space-air-ground integrated networks | 2024 | Paper | |
| Enabling mobile ai agent in 6g era: Architecture and key technologies | 2024 | Paper | |
| Llm agents as 6g orchestrator: A paradigm for task-oriented physical-layer automation | 2024 | Paper | |
| When large language model agents meet 6g networks: Perception, grounding, and alignmen | 2024 | Paper | |
| Airvista: Empowering uavs with 3d spatial reasoning abilities through a multimodal large language model agent | 2024 | Paper | |
| Agent-as-a-judge:Evaluate agents with agents | 2024 | Paper | Code |
| A survey of agent interoperability protocols: Model context protocol (mcp), agent communication protocol (acp), agent-to-agent protocol (a2a), and agent network protocol (anp) | 2025 | Paper | |
| Ai agents vs. agentic ai: A conceptual taxonomy, applications and challenge | 2025 | Paper | |
| Self-resource allocation in multi-agent llm systems | 2025 | Paper | |
| Model context protocol-based internet of experts for wireless environment-aware llm agents | 2025 | Paper | |
| Agent-driven generative semantic communication with cross-modality and prediction | 2025 | Paper | |
| Wirelessagent: Large language model agents for intelligent wireless networks | 2025 | Paper | Code |
| Agentic ai: Autonomous intelligence for complex goals–a comprehensive survey | 2025 | Paper | |
| From llm reasoning to autonomous ai agents: A comprehensive review | 2025 | Paper | |
| Agentic ai for scientific discovery: A survey of progress, challenges | 2025 | Paper | |
| Agentic reasoning: Reasoning llms with tools for the deep research | 2025 | Paper | Code |
| Towards agentic ai networking in 6g: A generative foundation model-as-agent approach | 2025 | Paper | |
| Llm-driven agentic ai approach to enhanced o-ran resilience in next-generation networks | 2025 | Paper | |
| Exploring llm-based multi-agent situation awareness for zero-trust space-air-ground integrated network | 2025 | Paper | Code |
| Scenario-driven evaluation of autonomous agents: Integrating large language model for uav mission reliability | 2025 | Paper | |
| Task offloading with llm-enhanced multi-agent reinforcement learning in uav-assisted edge computing | 2025 | Paper | |
| Uav-codeagents: Scalable uav mission planning via multi-agent react and vision-language reasoning | 2025 | Paper | |
| Agentic retrievalaugmented generation: A survey on agentic rag | 2025 | Paper | Code |
| Agentnet: Decentralized evolutionary coordination for llm-based multi-agent systems | 2025 | Paper | |
| Usercentrix: An agentic memory-augmented ai framework for smart spaces | 2025 | Paper | Code |
| Multi-agent collaboration mechanisms: A survey of llms | 2025 | Paper | Code |
| Advancing multi-agent systems through model context protocol: Architecture, implementation, and applications | 2025 | Paper | |
| Building a secure agentic ai application leveraging a2a protocol | 2025 | Paper | Code |
| Survey on evaluation of llm-based agents | 2025 | Paper |
Here is the list of our student contributors in each section.
| Section | Student Contributors |
|---|---|
| The whole paper | Zhengyu Du , Yuhan Zhang |
| Literature Search | Jian Zou , Dandan Qi |
| Project Maintenance | Xitao Pan |
If you intend to add or update the source code in the repository, please contact the following email addresses: jiangfb@hunnu.edu.cn, Dlj2017@hunnu.edu.cn, 240620854087@stu.hutb.edu.cn and 240620854065@stu.hutb.edu.cn.
| Version | Time | Update Content |
|---|---|---|
| v1 | 2025/5/23 | The initial version. |
| v2 | 2025/6/2 | Improve the writing. Correct some minor errors. |
| v3 | Improve the writing. Correct some minor errors. |
@ARTICLE{2025arXiv:2505.22311,
title = {From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications},
author = {Feibo Jiang, Cunhua Pan, Li Dong, Kezhi Wang, Octavia A. Dobre, Merouane Debbah},
journal = {arXiv preprint arXiv:2505.22311v1},
year = {2025}
}