用树搜索动态分解复杂优化问题，提升大模型建模准确率
OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modeling
- 构建分层问题树，按复杂度组织建模思路
- 在挑战性数据集上建模准确率提升超10%
- 适合需要自动化建模的运筹学研究与工程应用
优化建模是运筹学中最关键但技术性极强的环节。现有工作利用大语言模型（LLM）通过固定步骤分解任务来生成变量、约束和目标，但由于运筹学问题固有的复杂数学结构，标准分解方法往往表现不佳。为此，我们提出OptiTree，一种基于树搜索的新方法，通过自适应地将复杂问题分解为更简单的子问题，以增强建模能力。具体而言，我们构建了一个建模树，依据问题的层次化分类与复杂度组织各类运筹学问题，每个节点代表一类问题并包含相应的高层次建模思路。给定待建模问题时，通过递归搜索该树识别一系列简单子问题，并通过自适应整合层次化思路生成全局建模方案。实验表明，OptiTree显著优于当前最优方法，在挑战性基准上建模准确率提升超过10%。代码已开源：https://github.com/MIRALab-USTC/OptiTree/tree/main。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。