Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Toward 6G Native-AI Network: Foundation Model based Cloud-Edge-End Collaboration Framework

Xiang Chen, Zhiheng Guo, Xijun Wang, Howard H. Yang, Chenyuan Feng, Shuangfeng Han, Xiaoyun Wang, Tony Q. S. Quek

TL;DR

The paper tackles the challenge of realizing 6G-native AI by integrating foundation models with cloud–edge–end collaboration. It proposes a native AI framework built on three pillars: a communication-specific foundation model, an advanced retrieval-augmented generation system for expert knowledge, and hierarchical multi-agent collaboration. A cell-free massive MIMO orchestration case demonstrates that multi-agent planning and reflection can achieve higher sum rates and robustness, approaching the performance of perfect CSI. The work outlines practical challenges—data quality, standardization, and cost-performance tradeoffs—and provides future directions to enable scalable, low-latency deployment of native AI in 6G networks.

Abstract

Future wireless communication networks are in a position to move beyond data-centric, device-oriented connectivity and offer intelligent, immersive experiences based on multi-agent collaboration, especially in the context of the thriving development of pre-trained foundation models (PFM) and the evolving vision of 6G native artificial intelligence (AI). Therefore, redefining modes of collaboration between devices and agents, and constructing native intelligence libraries become critically important in 6G. In this paper, we analyze the challenges of achieving 6G native AI from the perspectives of data, AI models, and operational paradigm. Then, we propose a 6G native AI framework based on foundation models, provide an integration method for the expert knowledge, present the customization for two kinds of PFM, and outline a novel operational paradigm for the native AI framework. As a practical use case, we apply this framework for orchestration, achieving the maximum sum rate within a cell-free massive MIMO system, and presenting preliminary evaluation results. Finally, we outline research directions for achieving native AI in 6G.

Toward 6G Native-AI Network: Foundation Model based Cloud-Edge-End Collaboration Framework

TL;DR

The paper tackles the challenge of realizing 6G-native AI by integrating foundation models with cloud–edge–end collaboration. It proposes a native AI framework built on three pillars: a communication-specific foundation model, an advanced retrieval-augmented generation system for expert knowledge, and hierarchical multi-agent collaboration. A cell-free massive MIMO orchestration case demonstrates that multi-agent planning and reflection can achieve higher sum rates and robustness, approaching the performance of perfect CSI. The work outlines practical challenges—data quality, standardization, and cost-performance tradeoffs—and provides future directions to enable scalable, low-latency deployment of native AI in 6G networks.

Abstract

Future wireless communication networks are in a position to move beyond data-centric, device-oriented connectivity and offer intelligent, immersive experiences based on multi-agent collaboration, especially in the context of the thriving development of pre-trained foundation models (PFM) and the evolving vision of 6G native artificial intelligence (AI). Therefore, redefining modes of collaboration between devices and agents, and constructing native intelligence libraries become critically important in 6G. In this paper, we analyze the challenges of achieving 6G native AI from the perspectives of data, AI models, and operational paradigm. Then, we propose a 6G native AI framework based on foundation models, provide an integration method for the expert knowledge, present the customization for two kinds of PFM, and outline a novel operational paradigm for the native AI framework. As a practical use case, we apply this framework for orchestration, achieving the maximum sum rate within a cell-free massive MIMO system, and presenting preliminary evaluation results. Finally, we outline research directions for achieving native AI in 6G.
Paper Structure (24 sections, 5 figures)

This paper contains 24 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Research Challenges in 6G native AI
  3. Data Perspective
  4. Real-world Data
  5. Synthetic Data
  6. Standards and Technical Reports
  7. AI Model Perspective
  8. Communication-specific PFM
  9. Task-oriented AI Toolkit
  10. Operational Perspective
  11. Task Planning Mode
  12. Multi-agent Collaboration
  13. Native AI Framework for 6G Networks
  14. Architecture of the Native AI Framework
  15. Key Technologies
  16. ...and 9 more sections

Figures (5)

  • Figure 1: The proposed native AI framework with cloud-edge-end collaboration.
  • Figure 2: An illustration of the advanced RAG.
  • Figure 3: An illustration of hierarchical multi-agent collaboration.
  • Figure 4: A case study of task orchestration by multi-agent collaboration.
  • Figure 5: Performance comparison between our proposed framework with collaborative agents and three baseline schemes.