Draw2Learn: A Human-AI Collaborative Tool for Drawing-Based Science Learning
This work addresses the problem of scalable feedback for learners in science education, though it appears incremental as it builds on existing learning principles and AI applications.
The authors tackled the challenge of providing timely feedback in drawing-based science learning by developing Draw2Learn, a human-AI collaborative tool that generates structured drawing quests and delivers multidimensional feedback, with user feedback showing positive ratings for usability and usefulness.
Drawing supports learning by externalizing mental models, but providing timely feedback at scale remains challenging. We present Draw2Learn, a system that explores how AI can act as a supportive teammate during drawing-based learning. The design translates learning principles into concrete interaction patterns: AI generates structured drawing quests, provides optional visual scaffolds, monitors progress, and delivers multidimensional feedback. We collected formative user feedback during system development and open-ended comments. Feedback showed positive ratings for usability, usefulness, and user experience, with themes highlighting AI scaffolding value and learner autonomy. This work contributes a design framework for teammate-oriented AI in generative learning and identifies key considerations for future research.