Skip to main navigation Skip to search Skip to main content

ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges

  • Cheng Qian
  • , Hongyi Du
  • , Hongru Wang
  • , Xiusi Chen
  • , Yuji Zhang
  • , Avirup Sil
  • , Chengxiang Zhai
  • , Kathleen McKeown
  • , Heng Ji

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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 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.

Original languageEnglish (US)
Title of host publicationEMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025
EditorsChristos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
PublisherAssociation for Computational Linguistics (ACL)
Pages1599-1633
Number of pages35
ISBN (Electronic)9798891763357
DOIs
StatePublished - 2025
Event30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025 - Suzhou, China
Duration: Nov 4 2025 → Nov 9 2025

Publication series

NameEMNLP 2025 - 2025 Conference on Empirical Methods in Natural Language Processing, Findings of EMNLP 2025

Conference

Conference30th Conference on Empirical Methods in Natural Language Processing, EMNLP 2025
Country/TerritoryChina
CitySuzhou
Period11/4/25 → 11/9/25

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges'. Together they form a unique fingerprint.

Cite this