BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Teng, Yu, Wing-Yin, He, Zhenqi, Liu, Zehua, Gong, Hailei, Wu, Han, Han, Xiongwei, Shi, Wei, She, Ruifeng, Zhu, Fangzhou, Zhong, Tao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913858946334720
author Wang, Teng
Yu, Wing-Yin
He, Zhenqi
Liu, Zehua
Gong, Hailei
Wu, Han
Han, Xiongwei
Shi, Wei
She, Ruifeng
Zhu, Fangzhou
Zhong, Tao
author_facet Wang, Teng
Yu, Wing-Yin
He, Zhenqi
Liu, Zehua
Gong, Hailei
Wu, Han
Han, Xiongwei
Shi, Wei
She, Ruifeng
Zhu, Fangzhou
Zhong, Tao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17404
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving
Wang, Teng
Yu, Wing-Yin
He, Zhenqi
Liu, Zehua
Gong, Hailei
Wu, Han
Han, Xiongwei
Shi, Wei
She, Ruifeng
Zhu, Fangzhou
Zhong, Tao
Artificial Intelligence
Computation and Language
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.
title BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2411.17404