From Large Language Models and Optimization to Decision Optimization CoPilot: A Research Manifesto
Segev Wasserkrug, Leonard Boussioux, Dick den Hertog, Farzaneh Mirzazadeh, Ilker Birbil, Jannis Kurtz, Donato Maragno
TL;DR
The paper argues that broad access to optimization for real-world decisions can be achieved by merging Large Language Models (LLMs) with optimization modeling, through a Decision Optimization CoPilot (DOCP) that converses in natural language to elicit problems, generate models, and produce actionable solutions. It surveys the state of the art, presents experiments with ChatGPT to evaluate three core DOCP requirements (problem-to-model translation, model validation for non-experts, and producing efficient formulations), and identifies substantial gaps in abstraction, validation, and efficiency. The authors propose a multi-direction research agenda—encompassing LLM adaptation, reasoning architectures, validation tools, and benchmarks—to realize DOCP and enable widespread, better decision-making. They stress that even incremental tooling can democratize optimization, while calling for careful validation, human oversight, and ethical considerations in high-stakes contexts. The work serves as both a manifesto and a roadmap for cross-disciplinary collaboration between the LLM and optimization communities.
Abstract
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.