用多专家协作框架提升数学作业错题识别准确率
MathAgent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection
- 分三阶段由专用模块处理图文一致性、视觉语义和综合分析
- 错步识别准确率比基线高约5%，错误分类提升3%
- 已落地百万学生平台，满意度近90%，大幅降低人工成本
教育场景中的数学错误检测对多模态大语言模型（MLLM）构成重大挑战，需同时理解图文数学内容并进行复杂推理。尽管在解题上表现良好，现有MLLM在识别和分类学生多模态解题错误时仍显不足。为此，我们提出MathAgent——一种专为该任务设计的多数学代理混合框架。其将错误检测分为三个阶段：图像-文本一致性验证、视觉语义解析与集成错误分析，由专用代理分别处理，显式建模多模态问题与学生解题步骤间的关联。我们在真实教育数据上评估，结果显示，相比基线模型，错步识别准确率提升约5%，错误分类性能提高3%。此外，MathAgent已在教育平台实际部署，服务超百万名中小学生，学生满意度接近90%，显著降低人工检测成本。
原文摘要 · Abstract (English)
Mathematical error detection in educational settings presents a significant challenge for Multimodal Large Language Models (MLLMs), requiring a sophisticated understanding of both visual and textual mathematical content along with complex reasoning capabilities. Though effective in mathematical problem-solving, MLLMs often struggle with the nuanced task of identifying and categorizing student errors in multimodal mathematical contexts. Therefore, we introduce MathAgent, a novel Mixture-of-Math-Agent framework designed specifically to address these challenges. Our approach decomposes error detection into three phases, each handled by a specialized agent: an image-text consistency validator, a visual semantic interpreter, and an integrative error analyzer. This architecture enables more accurate processing of mathematical content by explicitly modeling relationships between multimodal problems and student solution steps. We evaluate MathAgent on real-world educational data, demonstrating approximately 5% higher accuracy in error step identification and 3% improvement in error categorization compared to baseline models. Besides, MathAgent has been successfully deployed in an educational platform that has served over one million K-12 students, achieving nearly 90% student satisfaction while generating significant cost savings by reducing manual error detection.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。