Methodologies for Improving the Quality of AI Tutoring in K-12 Education
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 9 of its 26 references that are in the map. First posted on arXiv 7 Aug 2026.
Builds on
9 of 26 references.
References · 9
- 2024A Survey on LLM-as-a-Judgecited by 1,423
- 2023Prediction-Powered Inferencecited by 220
- 2023Practical and Ethical Challenges of Large Language Models in Education: A Systematic Scoping Reviewcited by 83
- 2024Towards Responsible Development of Generative AI for Education: An Evaluation-Driven Approachcited by 54
- 2025MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutorscited by 49
- 2023Opportunities and Challenges in Neural Dialog Tutoringcited by 33
- 2025Can Large Language Models Match Tutoring System Adaptivity? A Benchmarking Studycited by 18
- 2024Using Large Language Models to Assess Tutors' Performance in Reacting to Students Making Math Errorscited by 9
- 2025Pedagogy-driven Evaluation of Generative AI-powered Intelligent Tutoring Systemscited by 5
Built on by
Not cited yet.