From Large Language Models and Optimization to Decision Optimization CoPilot: A Research Manifesto
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909120139886592 |
|---|---|
| author | Wasserkrug, Segev Boussioux, Leonard Hertog, Dick den Mirzazadeh, Farzaneh Birbil, Ilker Kurtz, Jannis Maragno, Donato |
| author_facet | Wasserkrug, Segev Boussioux, Leonard Hertog, Dick den Mirzazadeh, Farzaneh Birbil, Ilker Kurtz, Jannis Maragno, Donato |
| contents | Significantly simplifying the creation of optimization models for real-world business problems has long been a major goal in applying mathematical optimization more widely to important business and societal decisions. The recent capabilities of Large Language Models (LLMs) present a timely opportunity to achieve this goal. Therefore, we propose research at the intersection of LLMs and optimization to create a Decision Optimization CoPilot (DOCP) - an AI tool designed to assist any decision maker, interacting in natural language to grasp the business problem, subsequently formulating and solving the corresponding optimization model. This paper outlines our DOCP vision and identifies several fundamental requirements for its implementation. We describe the state of the art through a literature survey and experiments using ChatGPT. We show that a) LLMs already provide substantial novel capabilities relevant to a DOCP, and b) major research challenges remain to be addressed. We also propose possible research directions to overcome these gaps. We also see this work as a call to action to bring together the LLM and optimization communities to pursue our vision, thereby enabling much more widespread improved decision-making. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_16269 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Large Language Models and Optimization to Decision Optimization CoPilot: A Research Manifesto Wasserkrug, Segev Boussioux, Leonard Hertog, Dick den Mirzazadeh, Farzaneh Birbil, Ilker Kurtz, Jannis Maragno, Donato Artificial Intelligence Machine Learning Optimization and Control Significantly simplifying the creation of optimization models for real-world business problems has long been a major goal in applying mathematical optimization more widely to important business and societal decisions. The recent capabilities of Large Language Models (LLMs) present a timely opportunity to achieve this goal. Therefore, we propose research at the intersection of LLMs and optimization to create a Decision Optimization CoPilot (DOCP) - an AI tool designed to assist any decision maker, interacting in natural language to grasp the business problem, subsequently formulating and solving the corresponding optimization model. This paper outlines our DOCP vision and identifies several fundamental requirements for its implementation. We describe the state of the art through a literature survey and experiments using ChatGPT. We show that a) LLMs already provide substantial novel capabilities relevant to a DOCP, and b) major research challenges remain to be addressed. We also propose possible research directions to overcome these gaps. We also see this work as a call to action to bring together the LLM and optimization communities to pursue our vision, thereby enabling much more widespread improved decision-making. |
| title | From Large Language Models and Optimization to Decision Optimization CoPilot: A Research Manifesto |
| topic | Artificial Intelligence Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2402.16269 |