OptiMUS：使用MIP求解器和大语言模型进行优化建模
OptiMUS: Optimization Modeling Using MIP Solvers and large language models
AI总结：
本文提出基于大语言模型的智能体OptiMUS，可从自然语言描述自动建模并求解MILP问题，并发布NLP4LP数据集，实验显示其求解问题数量接近基本LLM提示策略的两倍。
摘要：
优化问题广泛存在于从制造、分销到医疗保健的各个领域。然而，大多数此类问题仍然依靠人工启发式方法求解，而非由最先进的求解器最优求解，因为表述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采用。我们提出了OptiMUS，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表述和求解混合整数线性规划（MILP）问题。OptiMUS能够开发数学模型、编写和调试求解器代码、开发测试，并检查所生成解的有效性。为了对我们的智能体进行基准测试，我们提出了NLP4LP，这是一个包含线性规划（LP）和混合整数线性规划（MILP）问题的新数据集。我们的实验表明，OptiMUS求解的问题数量几乎是基本LLM提示策略的两倍。OptiMUS代码和NLP4LP数据集可在https://github.com/teshnizi/OptiMUS获取。
英文摘要：
Optimization problems are pervasive across various 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, as the expertise required to formulate and solve these problems limits the widespread adoption of optimization tools and techniques. We introduce OptiMUS, a Large Language Model (LLM)-based agent designed to formulate and solve MILP problems from their natural language descriptions. OptiMUS is capable of developing mathematical models, writing and debugging solver code, developing tests, and checking the validity of generated solutions. To benchmark our agent, we present NLP4LP, a novel dataset of linear programming (LP) and mixed integer linear programming (MILP) problems. Our experiments demonstrate that OptiMUS solves nearly twice as many problems as a basic LLM prompting strategy. OptiMUS code and NLP4LP dataset are available at \href{https://github.com/teshnizi/OptiMUS}{https://github.com/teshnizi/OptiMUS}
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。
