BPP-Search：增强思维树推理以解决数学建模问题
BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving
AI总结：
针对运筹学数据集缺乏建模过程标注的问题，提出StructuredOR数据集和BPP-Search算法，将强化学习与思维树结合，提升数学建模问题求解的准确性和效率。
摘要：
大型语言模型展现出高级推理能力，有望将自然语言问题转化为数学模型。然而，现有的运筹学领域开源数据集缺乏对建模过程（如变量定义）的详细标注，仅关注目标值，这阻碍了强化学习的应用。为解决此问题，我们发布了StructuredOR数据集，该数据集带有全面标签，捕获完整的数学建模过程。我们进一步提出BPP-Search算法，该算法利用束搜索、过程奖励模型和成对偏好算法，将强化学习集成到思维树结构中。该方法能够高效探索树结构，避免穷举搜索，同时提高准确性。在StructuredOR、NL4OPT和MAMO-ComplexLP数据集上的大量实验表明，BPP-Search显著优于最先进的方法。在基于树的推理中，BPP-Search在准确性和效率方面表现出色，能够更快地检索到正确解决方案。StructuredOR数据集可在Huggingface（https://huggingface.co/datasets/LLM4OR/StructuredOR）和GitHub（https://github.com/LLM4OR/StructuredOR）上获取。
英文摘要：
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 on Huggingface https://huggingface.co/datasets/LLM4OR/StructuredOR and GitHub https://github.com/LLM4OR/StructuredOR.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
