Presenters:
Chuan Heng Foh, University of Surrey, UK
Hao Zhou, Samsung Research America
Mahdi Boloursaz Mashhadi, University of Surrey, UK
Abstract:
The evolution toward AI-native 6G networks demands a shift from task-specific learning models to scalable, generalizable intelligence embedded directly within the network fabric. This tutorial introduces two converging technological pillars—network foundation models and telecom AI agents—that together enable self-learning, self-healing, and intent-driven 6G infrastructures. Inspired by recent advances in Transformer-based foundation models for network traffic, the tutorial explains how large-scale self-supervised models can learn the “language of network data,” achieving robust generalization across tasks such as traffic classification, prediction, and generation. It then presents telecom AI agents as a distributed multi-agent framework that embeds autonomous cognitive agents into 6G control and management planes, where agents powered by multimodal large language models and reinforcement learning cooperate through standardized interfaces to support decentralized decision-making, resilience, and zero-touch automation. By highlighting cross-layer synergies between foundation model intelligence and agent-based orchestration, the tutorial shows how networks can reason, negotiate, and adapt in real time, providing attendees with a unified perspective on designing AI-native 6G systems—from data foundations to decentralized cognition—along with insights into open research challenges and emerging standardization pathways.
Biographies:
Chuan Heng Foh received his M.Sc. degree from Monash University in 1999 and his Ph.D. degree from the University of Melbourne in 2002. After a brief appointment as a Lecturer at Monash University, he joined Nanyang Technological University, Singapore, as an Assistant Professor in 2002, where he served until 2012. He is currently an Associate Professor at the University of Surrey. He has authored or co-authored more than 190 refereed publications in international journals and conferences. His research interests include protocol design, machine learning applications, and performance analysis of computer networks, covering wireless LANs, mobile ad-hoc and sensor networks, vehicular networks, the Internet of Things, and 5G/6G and open RAN systems. He has served as Vice Chair (Europe/Africa) for the IEEE Technical Committee on Green Communications and Computing and is Vice-Chair of the IEEE Vehicular Technology Society Technical Committee on Mission Critical Communications. He also serves on several journal editorial boards and is a Senior Editor for IEEE Access.
Hao Zhou is a Senior Research Engineer whose work focuses on the intersection of machine learning and networked systems, particularly for 5G/6G communications and network security. He previously held a postdoctoral position at McGill University and completed his Ph.D. at the University of Ottawa between 2019 and 2023. His research interests include large language model–enabled wireless networks, explainable AI for network decision-making, and deployment of LLMs at the network edge and cloud. He received the Best Paper Award at IEEE ICC 2023 and the IEEE ComSoc CSIM Technical Committee Best Journal Paper Award in 2023. His doctoral thesis on machine learning–based optimization of large-scale systems earned the Faculty of Engineering’s Best Doctoral Thesis Award at the University of Ottawa.
Mahdi Boloursaz Mashhadi is a Lecturer at the 5G/6G Innovation Centre within the Institute for Communication Systems and a Surrey AI Fellow. His research lies at the intersection of AI and wireless communications, including learning-communication co-design, generative AI for telecommunications, Token Communications, and collaborative machine learning. Prior to joining Surrey, he was a postdoctoral research associate at Imperial College London from 2019 to 2021. He has co-organized and chaired numerous workshops, tutorials, and special sessions on AI/ML for wireless communications at major IEEE venues such as ICC, ICMLCN, SPAWC, and GLOBECOM. He has served as a panel judge for the International Telecommunication Union’s AI/ML in 5G challenge and as a Technical Program Committee member and reviewer for leading IEEE conferences and journals. He is also an Associate Editor for the Springer Nature Wireless Personal Communications journal.