OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models

TL;DR

OptiMUS leverages large language models to automatically formulate, solve, and improve optimization problems from natural language, significantly outperforming existing methods especially on complex datasets.

Contribution

This paper introduces OptiMUS, a novel LLM-based system that automates the modeling and solving of (MI)LP problems from natural language descriptions, enhancing scalability and performance.

Findings

Outperforms state-of-the-art methods by over 20% on easy datasets.

Achieves over 30% improvement on complex datasets, including a new dataset NLP4LP.

Demonstrates effective handling of long and complex problem descriptions.

Abstract

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 $30\%$.