@inproceedings{qian-etal-2025-modelingagent,
    title = "{M}odeling{A}gent: Bridging {LLM}s and Mathematical Modeling for Real-World Challenges",
    author = "Qian, Cheng  and
      Du, Hongyi  and
      Wang, Hongru  and
      Chen, Xiusi  and
      Zhang, Yuji  and
      Sil, Avirup  and
      Zhai, ChengXiang  and
      McKeown, Kathleen  and
      Ji, Heng",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.85/",
    doi = "10.18653/v1/2025.findings-emnlp.85",
    pages = "1599--1633",
    ISBN = "979-8-89176-335-7",
    abstract = "Recent progress in large language models (LLMs) has enabled substantial advances in solving mathematical problems. However, existing benchmarks often fail to reflect real-world complexity, which demand open-ended, interdisciplinary reasoning and integration of computational tools. To address this gap, we introduce **ModelingBench**, a novel benchmark featuring real-world-inspired, open-ended problems from math modeling competitions across diverse domains, ranging from urban traffic optimization to ecosystem resource planning. These tasks require translating natural language into formal mathematical formulations, applying appropriate tools, and producing structured, defensible reports. ModelingBench supports multiple valid solutions, capturing the ambiguity and creativity of practical modeling. To solve these challenges, we present **ModelingAgent**, a multi-agent framework that coordinates tool use, supports structured workflows, and enables iterative self-refinement to generate well-grounded, creative solutions. Empirical results show that ModelingAgent substantially outperforms strong baselines and often produces solutions indistinguishable from those of human experts. Together, our work provides a comprehensive framework for evaluating and advancing real-world problem-solving in open-ended, interdisciplinary modeling challenges. All the codes are released for future research."
}