@inproceedings{yan-etal-2025-mathagent,
    title = "{M}ath{A}gent: Leveraging a Mixture-of-Math-Agent Framework for Real-World Multimodal Mathematical Error Detection",
    author = "Yan, Yibo  and
      Wang, Shen  and
      Huo, Jiahao  and
      Yu, Philip S.  and
      Hu, Xuming  and
      Wen, Qingsong",
    editor = "Rehm, Georg  and
      Li, Yunyao",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-industry.7/",
    pages = "69--82",
    ISBN = "979-8-89176-288-6",
    abstract = "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** specifically designed to address these challenges. Our approach decomposes error detection into three phases with specialized agents: an image-text consistency validator, a visual semantic interpreter, and an integrative error analyzer. This architecture enables more accurate processing of multimodal mathematical content by explicitly modeling the 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. Furthermore, MathAgent has been successfully deployed in an educational platform serving over one million K-12 students, achieving nearly 90{\%} student satisfaction while generating significant cost savings by reducing manual error detection."
}