0

Methodologies for Improving the Quality of AI Tutoring in K-12 Education

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.

Open
Preview
Year
2026
ArXiv
arxiv.org/abs/2608.11259
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2608.11259ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

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.