AmIWrite: Exploring Scalable One-on-One Handwriting-Based Tutoring for Mathematical Problem-Solving with an LLM-Powered AI Tutor

要旨

Real-time handwriting interactions between tutors and students —where tutors observe individual problem-solving processes, provide personalized annotations, and adapt explanations based on students' work—are fundamental to effective STEM tutoring. However, scaling such personalized handwriting-based tutoring remains challenging—human tutors cannot be available to every student on demand, and current online platforms often fail to recreate equivalent learning experiences. As an initial step toward tackling this challenge, we present AmIWrite, an LLM-powered AI tutoring system for mathematical problem-solving that provides real-time co-speech handwriting interactions on tablet devices, instantiated here as a case study in linear algebra. We conducted a within-subjects study (N = 40) comparing AmIWrite to a text-based AI tutor on two linear algebra topics. Our case study demonstrates how a multimodal AI tutor can preserve the pedagogical benefits of handwriting-based math tutoring and offer a potential path toward more scalable one-on-one STEM tutoring.

著者
Ziyi Liu
Purdue University, West Lafayette, Indiana, United States
Yuzhao Chen
Purdue University, West Lafayette, Indiana, United States
Haoyu Ji
purdue university, West Lafayette, Indiana, United States
Runlin Duan
Purdue University, West Lafayette, Indiana, United States
Zhengzhe Zhu
Purdue University, West Lafayette, Indiana, United States
Xiyun Hu
Purdue University, West Lafayette , Indiana, United States
Kylie Peppler
University of California - Irvine, Irvine, California, United States
Karthik Ramani
Purdue University, West Lafayette, Indiana, United States

会議: CHI 2026

ACM CHI Conference on Human Factors in Computing Systems

セッション: AI Tutors and Learning Support Systems

P1 - Room 123
7 件の発表
2026-04-17 20:15:00
2026-04-17 21:45:00