Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured Validation

TL;DR

This paper introduces Step-Opt, a framework that enhances LLMs' ability to solve complex optimization problems in Operations Research through iterative data synthesis and structured validation, leading to state-of-the-art performance.

Contribution

The paper presents a novel iterative problem generation and validation framework, improving LLM fine-tuning for optimization modeling in OR tasks.

Findings

Achieved 17.01% improvement in accuracy on difficult problems.

Fine-tuned LLaMA-3-8B and Mistral-7B with the new framework.

Demonstrated superior performance on NL4OPT, MAMO, and IndustryOR benchmarks.

Abstract

Large Language Models (LLMs) have revolutionized various domains but encounter substantial challenges in tackling optimization modeling tasks for Operations Research (OR), particularly when dealing with complex problem. In this work, we propose Step-Opt-Instruct, a framework that augments existing datasets and generates high-quality fine-tuning data tailored to optimization modeling. Step-Opt-Instruct employs iterative problem generation to systematically increase problem complexity and stepwise validation to rigorously verify data, preventing error propagation and ensuring the quality of the generated dataset. Leveraging this framework, we fine-tune open-source LLMs, including LLaMA-3-8B and Mistral-7B, to develop Step-Opt--a model that achieves state-of-the-art performance on benchmarks such as NL4OPT, MAMO, and IndustryOR. Extensive experiments demonstrate the superior performance of Step-Opt, especially in addressing complex OR tasks, with a notable 17.01\% improvement in micro average accuracy on difficult problems. These findings highlight the effectiveness of combining structured validation with gradual problem refinement to advance the automation of decision-making processes using LLMs.The code and dataset are available at https://github.com/samwu-learn/Step.