arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.22192cs.AI
收藏

OptiTree:基于树搜索的层次化思维生成用于大语言模型优化建模

OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modeling

MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China(脑启发式感知与认知联合实验室,中国科学技术大学);Noah’s Ark Lab, Huawei Technologies(华为诺亚实验室);Tianjin University(天津大学)

Haoyang Liu, Jie Wang, Yuyang Cai, Xiongwei Han, Yufei Kuang, Jianye Hao

AI总结:

OptiTree通过树搜索自适应分解复杂优化问题为子问题,整合层次化思维,显著提升大语言模型优化建模的准确性,在基准上实现超10%提升。

摘要:

优化建模是运筹学(OR)中最关键但技术性最强的部分之一。为了自动化建模过程,现有工作利用大语言模型(LLMs),提示它们将任务分解为生成变量、约束和目标的步骤。然而,由于OR问题固有的高度复杂的数学结构,标准的固定步骤分解往往无法实现高性能。为了解决这一挑战,我们引入了OptiTree,一种新颖的树搜索方法,旨在通过将复杂问题自适应地分解为更简单的子问题来增强建模能力。具体而言,我们开发了一个建模树,该树基于层次化的问题分类法和复杂度组织广泛的OR问题,每个节点代表一个问题类别,并包含相关的高层建模思维。给定一个待建模的问题,我们递归地搜索该树以识别一系列更简单的子问题,并通过自适应地整合层次化思维来综合全局建模思维。实验表明,与最先进的方法相比,OptiTree显著提高了建模准确性,在具有挑战性的基准上实现了超过10%的提升。代码已在https://github.com/MIRALab-USTC/OptiTree/tree/main发布。

英文摘要:

Optimization modeling is one of the most crucial but technical parts of operations research (OR). To automate the modeling process, existing works have leveraged large language models (LLMs), prompting them to break down tasks into steps for generating variables, constraints, and objectives. However, due to the highly complex mathematical structures inherent in OR problems, standard fixed-step decomposition often fails to achieve high performance. To address this challenge, we introduce OptiTree, a novel tree search approach designed to enhance modeling capabilities for complex problems through adaptive problem decomposition into simpler subproblems. Specifically, we develop a modeling tree that organizes a wide range of OR problems based on their hierarchical problem taxonomy and complexity, with each node representing a problem category and containing relevant high-level modeling thoughts. Given a problem to model, we recurrently search the tree to identify a series of simpler subproblems and synthesize the global modeling thoughts by adaptively integrating the hierarchical thoughts. Experiments show that OptiTree significantly improves the modeling accuracy compared to the state-of-the-art, achieving over 10\% improvements on the challenging benchmarks. The code is released at https://github.com/MIRALab-USTC/OptiTree/tree/main.

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。

↑