发表机构
Stanford Graduate School of Education; Department of Computer Science（斯坦福大学教育研究生院; 计算机科学系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对中学数学图表可靠生成难的问题，引入智能工作流程，让 LLM 智能体评估并迭代改进生成的视觉效果，通过探索性评估确定改进关键领域，初步证明可提高 AI 生成数学图表的可靠性和教育价值。
AI 中文摘要
数学图表在 K12 教育中起着关键作用，既是问题组成部分，也是学生理解的支架。然而，包括大语言模型（LLMs）在内的当前人工智能工具，即便有详细描述，也难以可靠地生成准确且符合教学要求的视觉图表。因此，中学数学图表的可靠生成仍存在重大差距。为解决此问题，我们引入一种智能工作流程，使 LLM 智能体能够评估生成视觉效果的质量，并利用此反馈迭代改进其输出。这个自我改进循环旨在提高人工智能生成图表的准确性和教育适用性。我们的研究调查两个问题。第一，给定视觉质量的特定标准，LLMs 能否准确生成视觉辅助工具的质量保证问题？第二，给定有效的质量保证问题，视觉语言模型能否有效评估生成的 K12 视觉辅助工具，并利用结果反馈进行迭代改进？我们对智能工作流程进行了探索性评估，并确定了改进的关键领域，包括更强的空间推理以及生成的质量保证问题中对图表特征更全面的覆盖。我们的结果提供了初步证据，表明这种方法可以提高人工智能生成的数学图表的可靠性和教育价值。
英文摘要
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.
Comments13 pages, 9 figures. Exploratory course project on agentic workflows for generating and evaluating K 12 mathematical diagrams
