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

📅 2025-06-21
📈 Citations: 0
Influential: 0
📄 PDF

career value

186K/year
🤖 AI Summary
Large language models (LLMs) struggle with complex problem comprehension and precise mathematical modeling in operations research (OR) optimization tasks. To address this, we propose Step-Opt-Instruct—a novel framework that iteratively generates OR problems of progressively increasing complexity and incorporates a structured, stepwise validation mechanism to effectively prevent error propagation and enhance synthetic data quality. We apply supervised fine-tuning using this framework on LLaMA-3-8B and Mistral-7B. Experimental results demonstrate state-of-the-art performance across three major benchmarks—NL4OPT, MAMO, and IndustryOR—with a 17.01% improvement in micro-averaged accuracy on complex problems. The approach significantly strengthens generalization capability for multi-constraint, multi-objective decision-making tasks, advancing the frontier of natural-language-to-optimization modeling.

Technology Category

Application Category

📝 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.
Problem

Research questions and friction points this paper is trying to address.

Enhancing LLMs for complex optimization modeling tasks
Generating high-quality data via iterative synthesis and validation
Improving accuracy in Operations Research problem-solving
Innovation

Methods, ideas, or system contributions that make the work stand out.

Iterative problem generation for complexity
Stepwise validation ensures data quality
Fine-tunes LLMs for optimization tasks
🔎 Similar Papers
No similar papers found.
Y
Yang Wu
C2DL, Institute of Automation, Chinese Academy of Sciences
Y
Yifan Zhang
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing
Y
Yurong Wu
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing
Y
Yuran Wang
Dalian Minzu University
J
Junkai Zhang
C2DL, Institute of Automation, Chinese Academy of Sciences
J
Jian Cheng
C2DL, Institute of Automation, Chinese Academy of Sciences