🤖 AI Summary
Existing approaches to business optimization face bottlenecks including heavy reliance on human modeling experts, limited long-range logical reasoning capabilities of large language models (LLMs), scarcity of high-quality training data, and absence of domain-adapted evaluation metrics. Method: This paper proposes an AI-Copilot framework for production scheduling that integrates modular problem synthesis, structured prompt engineering, semantic correctness evaluation tailored for optimization modeling, and lightweight fine-tuning—enabling end-to-end automatic translation of natural-language requirements into solvable mathematical programming models. Contribution/Results: We introduce the first custom evaluation metric system that jointly addresses token-length constraints and modeling fidelity. Empirical results on complex, large-scale scheduling tasks demonstrate significant improvements over state-of-the-art baselines in both formalization accuracy and practical usability, substantially reducing dependence on domain experts.
📝 Abstract
Business optimisation refers to the process of finding and implementing efficient and cost-effective means of operation to bring a competitive advantage for businesses. Synthesizing problem formulations is an integral part of business optimisation, which relies on human expertise to construct problem formulations using optimisation languages. Interestingly, with advancements in Large Language Models (LLMs), the human expertise needed in problem formulation can be minimized. However, developing an LLM for problem formulation is challenging, due to training data, token limitations, and lack of appropriate performance metrics. For the requirement of training data, recent attention has been directed towards fine-tuning pre-trained LLMs for downstream tasks rather than training an LLM from scratch for a specific task. In this paper, we adopt an LLM fine-tuning approach and propose an AI-Copilot for business optimisation problem formulation. For token limitations, we introduce modularization and prompt engineering techniques to synthesize complex problem formulations as modules that fit into the token limits of LLMs. Additionally, we design performance evaluation metrics that are better suited for assessing the accuracy and quality of problem formulations. The experiment results demonstrate that with this approach we can synthesize complex and large problem formulations for a typical business optimisation problem in production scheduling.
