A Comprehensive Survey of Large AI Models for Future Communications: Foundations, Applications, and Challenges

Всесторонний обзор больших моделей искусственного интеллекта для будущих систем связи: основы, применения и проблемы
Dusit Tao Niyato, Merouane Abdelkader Debbah, Zhu Han, Cunhua Pan, Li Dong, Kezhi Wang, Feibo Jiang
2026-01-01

6G wireless communicationslarge AI modelslarge language modelsretrieval-augmented generationsemantic communication
The 6G wireless communications aim to establish an intelligent world of ubiquitous connectivity, providing an unprecedented communication experience. Large artificial intelligence models (LAMs) are characterized by significantly larger scales (e.g., billions or trillions of parameters) compared to typical artificial intelligence (AI) models. LAMs exhibit outstanding cognitive abilities, including strong generalization capabilities for fine-tuning to downstream tasks, and emergent capabilities to handle tasks unseen during training. Therefore, LAMs efficiently provide AI services for diverse communication applications, making them crucial tools for addressing complex challenges in future wireless communication systems. This study provides a comprehensive review of the foundations, applications, and challenges of LAMs in communication. First, we introduce the current state of AI-based communication systems, emphasizing the motivation behind integrating LAMs into communications and summarizing the key contributions. We then present an overview of the essential concepts of LAMs in communication. This includes an introduction to the main architectures of LAMs, such as transformer, diffusion models, and mamba. We also explore the classification of LAMs, including large language models (LLMs), large vision models (LVMs), large multimodal models (LMMs), and world models, and examine their potential applications in communication. Additionally, we cover the training methods and evaluation techniques for LAMs in communication systems. Lastly, we introduce optimization strategies such as chain of thought (CoT), retrieval augmented generation (RAG), and agentic systems. Following this, we discuss the research advancements of LAMs across various communication scenarios, including physical layer design, resource allocation and optimization, network design and management, edge intelligence, semantic communication, agentic systems, and emerging applications. Finally, we analyze the major challenges in current research, including the lack of high-quality and structured communication data, hallucination and limited reasoning in generative models, poor explainability and adaptability, deployment under resource constraints, as well as security and privacy risks, and provide insights into potential future directions.
1
Large artificial intelligence models, with billions or trillions of parameters, offer stronger generalization and emergent capabilities than typical AI models for future wireless communications.
2
Large models are reviewed across communication applications including physical-layer design, resource allocation, network management, edge intelligence, semantic communication, and agentic systems.
3
The paper summarizes training and evaluation methods for large models in communications and examines optimization strategies including chain-of-thought, retrieval-augmented generation, and agentic systems.
4
The survey identifies research challenges and opportunities involved in integrating large AI models into intelligent 6G communication systems.
5
The survey organizes communication-oriented large models by architectures, including transformers, diffusion models, and Mamba, and by model types such as LLMs, LVMs, LMMs, and world models.

large artificial intelligence models (LAMs) in future wireless communication systems

the foundations, architectures, applications, training and evaluation methods, optimization strategies, research advancements, and challenges of LAMs for 6G communications

Publication Details
Publication Date
2026-01-01
Journal
Publisher
ISSN
Cited by
80
Access Type
Author Information
Authors
Dusit Tao Niyato
Merouane Abdelkader Debbah
Zhu Han
Cunhua Pan
Li Dong
Kezhi Wang
Feibo Jiang
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%