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

TL;DR

The paper delivers a comprehensive survey of large AI models (LAMs) in future communications, detailing architectures (transformer, diffusion, mamba), classifications (LLMs, LVMs, LMMs, WM), and end-to-end training/evaluation/optimization pipelines in telecom settings. It maps LAMs to diverse 6G applications across physical layer design, resource allocation, network design/management, edge intelligence, semantic communication, and agentic systems, while highlighting emerging uses in healthcare, digital twins, AIoT, ISATNs, and UAV integration. The authors also systematically critique current challenges—data scarcity, lack of domain knowledge, hallucinations, reasoning limits, explainability, adaptability, edge constraints, latency, and privacy—and offer concrete directions (data gathering, physics-informed modeling, efficient fine-tuning, and privacy-preserving collaboration) to advance robust deployment. By synthesizing architectures, training/optimization strategies, and domain-specific applications, the work provides a practical roadmap for researchers and practitioners aiming to leverage LAMs to realize intelligent, high-performance 6G networks.

Abstract

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. Finally, we analyze the challenges in the current research and provide insights into potential future research directions.

Figures (4)

• Figure 1: The development history of LAMs.
• Figure 2: The role of LAMs in AI.
• Figure 3: Overall organization of the survey.
• Figure 4: Applications of LAMs in Communication. LAMs can be applied across various domains in communication, including physical layer design, resource allocation and optimization, network design and management, edge intelligence, semantic communication, agentic systems, and emerging applications.