Multi-Agent Large Language Models for Wireless Optimization and Forecasting
Large Language Models (LLMs) are poised to fundamentally reshape the design and operation of future wireless networks. Rather than relying solely on narrowly specialized optimization pipelines, emerging wireless systems may increasingly incorporate foundation models capable of reasoning, adaptation, and decision-making across diverse network tasks. This talk explores how large language models may drive a shift from conventional wireless optimization to foundation-model-driven intelligence in future 6G networks. The talk presents three complementary advances in LLM-driven wireless intelligence. First, multi-agent LLM frameworks for radio resource management are introduced for solving constrained non-convex optimization problems such as beamforming, power control, and user association through iterative prompting, evaluator-guided refinement, and uncertainty-aware reasoning. Second, the talk explores LLM-based wireless time-series forecasting, where specialized agents model trends and fluctuations in correlated network signals to enable predictive and adaptive network intelligence. Third, intelligent autonomous vehicular systems are considered through the joint optimization of vehicle-to-infrastructure (V2I) communications and autonomous driving policies. Across these applications, LLM-driven frameworks demonstrate adaptable and scalable wireless intelligence with reduced computational complexity and minimal task-specific retraining. The talk concludes by discussing the broader vision of unified foundation-model-driven architectures capable of enabling end-to-end intelligence for future wireless systems and 6G networks beyond traditional communication paradigms.
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
Loading virtual attendance info...
- Via del Politecnico
- Roma, Lazio
- Italy 00133
- Building: Macroarea di Ingegneria
- Room Number: Classroom C12
- Contact Event Hosts
- Co-sponsored by Tor Vergata University of Rome
Speakers
Hina Tabassum of York University, Canada
Biography:
Hina Tabassum (Senior Member, IEEE) received the Ph.D. degree from the King Abdullah University of Science and Technology. She is currently an Associate Professor with the Lassonde School of Engineering at York University, Canada, where she joined in 2018. She also serves as a Visiting Faculty member at University of Toronto and holds the York Research Chair in 5G/6G-enabled mobility and sensing applications. She was selected as an IEEE Communications Society Distinguished Lecturer for 2025–2026 and has been listed among Stanford’s World’s Top 2% Researchers from 2021 to 2025. She has earned numerous distinctions, including the N2Women Star in Networking and Communications (2025), Early Career Lassonde Innovation Award (2023), N2Women Rising Star in Networking and Communications (2022), and multiple Exemplary Editor awards from IEEE journals. She has authored over 120 refereed publications in leading IEEE journals and conferences. Her research focuses on 5G/6G wireless communications and sensing networks, connected and autonomous systems, and AI-enabled wireless resource management. Her recognitions include the N2Women Star in Networking and Communications (2025), the N2Women Rising Star Award (2022), and the Early Career Lassonde Innovation Award (2023). She currently serves as an editor for several leading IEEE journals, including IEEE Transactions on Communications, IEEE Transactions on Wireless Communications, and IEEE Communications Surveys and Tutorials.