LLMs exhibit advanced reasoning capabilities, offering the potential to transform natural language questions into mathematical models. However, existing open-source datasets in operations research domain lack detailed annotations of the modeling process, such as variable definitions, focusing solely on objective values, which hinders reinforcement learning applications. To address this, we release the StructuredOR dataset, annotated with comprehensive labels that capture the complete mathematical modeling process. We further propose BPP-Search, an algorithm that integrates reinforcement learning into a tree-of-thought structure using Beam search, a Process reward model, and a pairwise Preference algorithm. This approach enables efficient exploration of tree structures, avoiding exhaustive search while improving accuracy. Extensive experiments on StructuredOR, NL4OPT, and MAMO-ComplexLP datasets show that BPP-Search significantly outperforms state-of-the-art methods. In tree-based reasoning, BPP-Search excels in accuracy and efficiency, enabling faster retrieval of correct solutions. The StructuredOR dataset is available atthis https URL.
View on arXiv@article{wang2025_2411.17404,
title={ BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving },
author={ Teng Wang and Wing-Yin Yu and Zhenqi He and Zehua Liu and Hailei Gong and Han Wu and Xiongwei Han and Wei Shi and Ruifeng She and Fangzhou Zhu and Tao Zhong },
journal={arXiv preprint arXiv:2411.17404},
year={ 2025 }
}