OptiMUS-0.3: Using Large Language Models to Model and Solve Optimization Problems at Scale
This addresses the problem of limited adoption of optimization tools due to expertise barriers, offering a scalable solution for sectors like manufacturing and healthcare, though it is incremental as it builds on existing LLM capabilities.
The paper tackles the challenge of formulating and solving optimization problems from natural language descriptions by introducing an LLM-based system, OptiMUS-0.3, which outperforms existing methods by over 22% on easy datasets and 24% on hard datasets.
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. We introduce a Large Language Model (LLM)-based system designed to formulate and solve (mixed integer) linear programming problems from their natural language descriptions. Our system is capable of developing mathematical models, writing and debugging solver code, evaluating the generated solutions, and improving efficiency and correctness of its model and code based on these evaluations. OptiMUS-0.3 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-0.3 outperforms existing state-of-the-art methods on easy datasets by more than 22% and on hard datasets (including a new dataset, NLP4LP, released with this paper that features long and complex problems) by more than 24%.