Saved in:
Bibliographic Details
Main Authors: Chen, Steven-Shine, Lee, Jimin, Liang, Paul Pu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.16434
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915222737911808
author Chen, Steven-Shine
Lee, Jimin
Liang, Paul Pu
author_facet Chen, Steven-Shine
Lee, Jimin
Liang, Paul Pu
contents Humans have long relied on visual aids like sketches and diagrams to support reasoning and problem-solving. Visual tools, like auxiliary lines in geometry or graphs in calculus, are essential for understanding complex ideas. However, many tutoring systems remain text-based, providing feedback only through natural language. Leveraging recent advances in Large Multimodal Models (LMMs), this paper introduces Interactive Sketchpad, a tutoring system that combines language-based explanations with interactive visualizations to enhance learning. Built on a pre-trained LMM, Interactive Sketchpad is fine-tuned to provide step-by-step guidance in both text and visuals, enabling natural multimodal interaction with the student. Accurate and robust diagrams are generated by incorporating code execution into the reasoning process. User studies conducted on math problems such as geometry, calculus, and trigonometry demonstrate that Interactive Sketchpad leads to improved task comprehension, problem-solving accuracy, and engagement levels, highlighting its potential for transforming educational technologies. All code is available at: https://stevenshinechen.github.io/interactivesketchpad/.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16434
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Interactive Sketchpad: A Multimodal Tutoring System for Collaborative, Visual Problem-Solving
Chen, Steven-Shine
Lee, Jimin
Liang, Paul Pu
Human-Computer Interaction
Artificial Intelligence
Humans have long relied on visual aids like sketches and diagrams to support reasoning and problem-solving. Visual tools, like auxiliary lines in geometry or graphs in calculus, are essential for understanding complex ideas. However, many tutoring systems remain text-based, providing feedback only through natural language. Leveraging recent advances in Large Multimodal Models (LMMs), this paper introduces Interactive Sketchpad, a tutoring system that combines language-based explanations with interactive visualizations to enhance learning. Built on a pre-trained LMM, Interactive Sketchpad is fine-tuned to provide step-by-step guidance in both text and visuals, enabling natural multimodal interaction with the student. Accurate and robust diagrams are generated by incorporating code execution into the reasoning process. User studies conducted on math problems such as geometry, calculus, and trigonometry demonstrate that Interactive Sketchpad leads to improved task comprehension, problem-solving accuracy, and engagement levels, highlighting its potential for transforming educational technologies. All code is available at: https://stevenshinechen.github.io/interactivesketchpad/.
title Interactive Sketchpad: A Multimodal Tutoring System for Collaborative, Visual Problem-Solving
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2503.16434