Demystifying 6G AI-RAN: A New Paradigm for Intent-Driven Networking and Edge AI Services

As 6G networks evolve beyond traditional performance-centric architectures, a transformative paradigm is emerging—AI-native Radio Access Networks (AI-RAN)—that fuse semantic intelligence, autonomous decision-making, and large-scale AI models at the edge. This tutorial offers a comprehensive exploration of the key technologies, design principles, and research frontiers underpinning the development of intent-understanding, agent-driven, and semantically aware RANs. This tutorial begins by examining how distributed AI is being embedded across the RAN hierarchy, from Non-RT to Near-RT RICs, enabling low-latency adaptation, cross-layer reasoning, and autonomous control. We then delve into the architecture of semantic-aware RAN—a novel concept that integrates semantic communication layers with native AI to achieve task-oriented, context-aware networking. Special focus is placed on the rise of multi-agent systems (e.g., LLM-based xApps) that act as goal-driven entities within the O-RAN framework, supporting functions such as real-time optimization, fault detection, and policy planning. Finally, we address emerging techniques for efficient fine-tuning and deployment of foundation models (e.g., LLMs) at the network edge, covering methods like parameter-efficient adaptation, distillation, and on-device inference acceleration. The tutorial aims to equip researchers and practitioners with a forward-looking understanding of how 6G AI-RAN will enable intent-driven services, intelligent coordination, and distributed cognition across the wireless edge.

  • Corresponding Author Information
    Tony Q. S. Quek, Singapore University of Technology and Design (SUTD), Singapore

    Tony Q. S. Quek received the B.E. and M.E. degrees from the Tokyo Institute of Technology in 1998 and 2000, respectively, and the Ph.D. degree from the Massachusetts Institute of Technology (MIT) in 2008. Currently, he is the Associate Provost for AI and Digital Innovation at Singapore University of Technology and Design (SUTD), the Director of the Future Communications R&D Programme. His research topics include wireless communications, network intelligence, non-terrestrial networks, open radio access network, and 6G. Dr. Quek was honored with 2008 Philip Yeo Prize for Outstanding Achievement in Research, 2012 IEEE William R. Bennett Prize, 2016 IEEE Signal Processing Society Young Author Best Paper Award, 2017 IEEE ComSoc AP Outstanding Paper Award, 2020 IEEE Communications Society Young Author Best Paper Award, 2020 IEEE Stephen O. Rice Prize and 2022 IEEE Signal Processing Society Best Paper Award. He is AI-on-RAN Working Group Chair in AI-RAN Alliance.
    He is a Fellow of IEEE, a Fellow of WWRF, and a Fellow of the Academy of Engineering Singapore.

  • Speaker 1: Howard H. Yang, Zhejiang University, China
  • Presentation Title: A Tale of Interference in Distributed Machine Learning Over-the-Air

    Howard H. Yang received the B.E. degree from Harbin Institute of Technology (HIT), China, in 2012, the M.Sc. degree from Hong Kong University of Science and Technology (HKUST), Hong Kong, in 2013, and the Ph.D. degree from Singapore University of Technology and Design (SUTD), Singapore, in 2017. Currently, he is an assistant professor of Zhejiang University, and an adjunct assistant professor at the University of Illinois Urbana-Champaign, IL, USA. His research interests including modeling of modern wireless networks, high dimensional statistics, graph signal processing, and machine learning. He serves as an Associate Editor for the IEEE Transactions on Wireless Communications and an Editor-at-Large for the IEEE Open Journal of The Communications Society. He received the IEEE ComSoc Asia-Pacific Outstanding Young Researcher Award in 2023, the IEEE Signal Processing Society Best Paper Award in 2022, the IEEE WCSP 10-Year Anniversary Excellent Paper Award in 2019, and the IEEE WCSP Best Paper Award in 2014.


  • Speaker 2: Chenyuan Feng, University of Exeter, U.K.
  • Presentation Title: Toward 6G Native-AI RAN: A Semantic and Agentic Perspective

    Chenyuan Feng received the B.E. degree from the University of Electronic Science and Technology of China (UESTC), China, in 2016, and the Ph.D. degree from Singapore University of Technology and Design (SUTD), Singapore, in 2021, respectively. Currently, she is a research fellow at Department of Computer Science, University of Exeter, U.K.. Her research interests include edge intelligence and in-network AI. She is a receipt of 2021 IEEE ComComAp Best Paper Award, 2024 IEEE ICCT Best Paper Award, and 2025 IEEE ICCCS 10th Anniversary Best Paper Award. Dr. Feng delivered several tutorials and invited talks at International conferences, such as IEEE PIMRC'24, IEEE VCC'24, IEEE ICCT'22, ICCT'24 and IEEE VTC-Sping'25. Dr. Feng serves as an Associate Editor for the IEEE Internet of Things Journal and the IEEE Open Journal of the Communications Society. Dr. Feng is a Marie Skłodowska-Curie Scholar and 6G Rising Star Young Scientist.


  • Speaker 3: Zihan Chen, Singapore University of Technology and Design (SUTD), Singapore
  • Presentation Title: Efficient and scalable distibuted LLM fine-tuning within AI-RAN

    Zihan Chen received the B.Eng. degree in Communication Engineering from the Yingcai Honors College at the University of Electronic Science and Technology of China (UESTC) in 2018. He received his Ph.D. degree from the Singapore University of Technology and Design (SUTD)- National University of Singapore (NUS) Joint Ph.D. Program in 2022. Currently, he is a Postdoctoral Research Fellow at SUTD. His research mainly focuses on network intelligence, machine learning, and semantic communication.