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

Ali Ahmaditeshnizi, Wenzhi Gao, Madeleine Udell
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:577-596, 2024.

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 $30$%. The implementation and the datasets are available at https://github.com/teshnizi/OptiMUS.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-ahmaditeshnizi24a, title = {{O}pti{MUS}: Scalable Optimization Modeling with ({MI}){LP} Solvers and Large Language Models}, author = {Ahmaditeshnizi, Ali and Gao, Wenzhi and Udell, Madeleine}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {577--596}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/ahmaditeshnizi24a/ahmaditeshnizi24a.pdf}, url = {https://proceedings.mlr.press/v235/ahmaditeshnizi24a.html}, 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 $30$%. The implementation and the datasets are available at https://github.com/teshnizi/OptiMUS.} }
Endnote
%0 Conference Paper %T OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models %A Ali Ahmaditeshnizi %A Wenzhi Gao %A Madeleine Udell %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-ahmaditeshnizi24a %I PMLR %P 577--596 %U https://proceedings.mlr.press/v235/ahmaditeshnizi24a.html %V 235 %X 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 $30$%. The implementation and the datasets are available at https://github.com/teshnizi/OptiMUS.
APA
Ahmaditeshnizi, A., Gao, W. & Udell, M.. (2024). OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:577-596 Available from https://proceedings.mlr.press/v235/ahmaditeshnizi24a.html.

Related Material