OptiMUS:基于(MI)LP求解器与大语言模型的可扩展优化建模
OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models
AI总结:
本文提出基于大语言模型的智能体OptiMUS,能根据自然语言描述构建并求解(混合整数)线性规划问题,通过模块化结构处理长文本与复杂数据,在简单和困难数据集上分别比现有最优方法提升20%和30%以上。
摘要:
优化问题在从制造和分销到医疗保健的各个领域中无处不在。然而,大多数此类问题仍然通过手工启发式地解决,而不是使用最先进的求解器进行最优求解,因为构建和求解这些问题所需的专业知识限制了优化工具和技术的广泛应用。本文介绍了OptiMUS,这是一个基于大语言模型(LLM)的智能体,旨在根据自然语言描述来构建和求解(混合整数)线性规划问题。OptiMUS能够开发数学模型,编写和调试求解器代码,评估生成的解决方案,并基于这些评估改进其模型和代码。OptiMUS利用模块化结构来处理问题,使其能够处理描述冗长且数据复杂的问题,而无需长提示。实验表明,OptiMUS在简单数据集上比现有最先进方法高出20%以上,在困难数据集(包括随本文发布的新数据集NLP4LP,其特点是包含冗长且复杂的问题)上高出30%以上。
英文摘要:
Optimization problems are pervasive in sectors from manufacturing and distribution to healthcare. However, most such problems are still solved heuristically by hand rather than optimally by state-of-the-art solvers because the expertise required to formulate and solve these problems limits the widespread adoption of optimization tools and techniques. This paper introduces OptiMUS, a Large Language Model (LLM)-based agent designed to formulate and solve (mixed integer) linear programming problems from their natural language descriptions. OptiMUS can develop mathematical models, write and debug solver code, evaluate the generated solutions, and improve its model and code based on these evaluations. OptiMUS utilizes a modular structure to process problems, allowing it to handle problems with long descriptions and complex data without long prompts. Experiments demonstrate that OptiMUS outperforms existing state-of-the-art methods on easy datasets by more than $20\%$ and on hard datasets (including a new dataset, NLP4LP, released with this paper that features long and complex problems) by more than $30\%$.
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。