MAIC-UI: Making Interactive Courseware with Generative UI

2026-04-28

AI Summary

This work addresses the challenge that traditional STEM interactive courseware development relies heavily on front-end programming, and existing authoring tools struggle to balance pedagogical accuracy with rapid iteration. To overcome this, the paper proposes a zero-code courseware authoring system that ensures content rigor through structured knowledge analysis, multimodal understanding, and a two-stage generate-validate-optimize pipeline. The system innovatively introduces a Click-to-Locate interaction mechanism and a Unified Diff–based incremental generation approach, enabling sub-second interactive editing. User studies demonstrate a 30% reduction in editing iterations and significantly improved learner controllability. In a three-month classroom deployment, students in the experimental group showed a 9.21-point gain in STEM performance, while the control group declined by 2.32 points.

Abstract

Creating interactive STEM courseware traditionally requires HTML/CSS/JavaScript expertise, leaving barriers for educators. While generative AI can produce HTML codes, existing tools generate static presentations rather than interactive simulations, struggle with long documents, and lack pedagogical accuracy mechanisms. Furthermore, full regeneration for modifications requires 200--600 seconds, disrupting creative flow. We present MAIC-UI, a zero-code authoring system that enables educators to create and rapidly edit interactive courseware from textbooks, PPTs, and PDFs. MAIC-UI employs: (1) structured knowledge analysis with multi-modal understanding to ensure pedagogical rigor; (2) a two-stage generate-verify-optimize pipeline separating content alignment from visual refinement; and (3) Click-to-Locate editing with Unified Diff-based incremental generation achieving sub-10-second iteration cycles. A controlled lab study with 40 participants shows MAIC-UI reduces editing iterations (4.9 vs. 7.0) and significantly improves learnability and controllability compared to direct Text-to-HTML generation. A three-month classroom deployment with 53 high school students demonstrates that MAIC-UI fosters learning agency and reduces outcome disparities -- the pilot class achieved 9.21-point gains in STEM subjects compared to -2.32 points in control classes. Our code is available at https://github.com/THU-MAIC/MAIC-UI.

Problem

• interactive courseware
• generative AI
• STEM education
• pedagogical accuracy
• zero-code authoring

Innovation

• generative UI
• zero-code authoring
• interactive courseware
• incremental generation
• pedagogical accuracy