Methodologies for Improving the Quality of AI Tutoring in K-12 Education
arXiv:2608.11259 · doi:10.1007/978-3-032-29755-6_14
Abstract
Many AI tutors leverage large language models (LLMs) today. Given that LLMs are opaque black boxes, robust evaluation and live experimentation to measure the impact of every change are essential. We pioneered AI-powered tutoring for K-12 with the launch of Khanmigo (Khan Academy, 2023). We describe the metrics we use to measure AI tutoring quality and student engagement as well as various experiments we have run. We highlight the changes that have moved our metrics, including models, prompting, personalization and agents.
15 pages. Accepted at AIED 2026 (27th International Conference on Artificial Intelligence in Education). Published version: Artificial Intelligence in Education, LNCS vol. 16582, Springer, Cham, first online 25 June 2026 (cite as 2027)