Abstract
Mathematical diagrams play a crucial role in K-12 education, both as problem components and as scaffolding for student comprehension. However, current AI tools, including Large Language Models (LLMs), struggle to reliably generate accurate and pedagogically sound visual diagrams, even when provided with detailed descriptions. A significant gap therefore remains in the reliable generation of diagrams for middle school mathematics.
To address this, we introduce an agentic workflow that enables LLM agents to evaluate the quality of generated visuals and use this feedback to iteratively improve their outputs. This self-improvement loop aims to enhance the accuracy and educational appropriateness of AI-generated diagrams.
Our research investigates two questions. First, can LLMs accurately generate quality assurance questions for a visual aid given specific criteria for visual quality? Second, given valid quality assurance questions, can Vision Language Models effectively evaluate generated K-12 visual aids and use the resulting feedback to improve them iteratively?
We conduct an exploratory evaluation of our agentic workflow and identify key areas for improvement, including stronger spatial reasoning and more comprehensive coverage of diagram features in the generated quality assurance questions. Our results provide preliminary evidence that this approach can improve the reliability and educational value of AI-generated mathematical diagrams.
Blogger's Review: The agentic workflow proposed in this paper offers a fresh perspective on AI applications in education, particularly in generating mathematical diagrams. Through the self-feedback mechanism, LLMs can not only generate diagrams but also continuously improve them, laying a foundation for future educational technology applications. The challenge lies in further enhancing the model's spatial reasoning capabilities to meet educational needs.