cs.CYAug 7, 2026

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

Authors: Tushar Udeshi, Anna Khazenzon, Kabir Khan, Nick Breen, RJ Corwin, Chris DiGiano, Kodi Weatherholtz, Marek Zaluski

Organizations: Khan Academy, Mountain View CA 94041, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Explore similar work

CardsList

  1. Knowledge Distillation for Automated AI Tutor Evaluation

    Jul 12, 2026Tahmid Al Hannan, Diego Garcia, Alex Njoroge +2TutorsPedagogy

  2. Beyond Helpfulness: A Teaching-over-Solving Diagnostic for Measuring Educational Impact in LLM Tutors

    Jun 15, 2026Junyi Yao, Zihao Zheng, Baichuan LiTutorsEducation

  3. Evaluating and Improving Pedagogical Fit in LLM-Based AI Tutors with the Pedagogical Suitability Index

    Aug 5, 2026Benjamin Barlog, Hudson Craig, Zedong PengTutorsPedagogy