Abstract
Join us in exploring how agentic AI tutors enable adaptive and personalized learning in real-world education systems
Recent advances in large language and multimodal models have enabled agentic AI tutors to operate autonomously in real-world education systems. This keynote presents how adaptive and personalized educational AI agents are designed and deployed at scale using state-of-the-art techniques, including multi-agent LLM reasoning, multimodal error analysis, dialog-driven interaction, and longitudinal learner modeling. Drawing on large-scale applications from Squirrel Ai Learning, the talk demonstrates how these AI tutors perform fine-grained misconception diagnosis, personalized feedback generation, and adaptive learning path optimization through continuous interaction with real student data. Validated through large-scale real-world deployments, this work highlights key technical lessons on reliability, robustness, and trust in smart education ecosystems.
Dr. Qingsong Wen
Squirrel Ai Learning, USA and University of Oxford, UK
Biography
Qingsong Wen is currently the Head of AI & Chief Scientist at Squirrel Ai Learning (a top EdTech unicorn), and PhD Supervisor at University of Oxford. Before that, he worked at Alibaba, Qualcomm, Marvell, etc., and received his M.S. and Ph.D. degrees from Georgia Institute of Technology, USA. His research interests include machine learning, data mining, and signal processing, especially AI for Time Series, AI for Education, LLM & AI Agent. He has published near 200 top-ranked AI conference and journal papers. Currently, he serves as Associate Vice President for Cybernetics of IEEE SMC Society, Chair of IEEE CIS Task Force on AI for Time Series and Spatio-Temporal Data, and Vice Chair of INNS AI for Education Section. He also regularly serves as Area Chair of the top AI conferences including NeurIPS, ICML, ICLR, KDD, etc, and (Senior) Associate Editor for IEEE TSP and IEEE TPAMI.
IEEE SWC 2026 Colocated Conferences
IEEE SWC 2026
IEEE Digital Twin 2026
IEEE METAVERSE 2026
IEEE ScalCom 2026
IEEE UIC 2026
IEEE ATC 2026
Sponsors
