Saved in:
Bibliographic Details
Main Authors: Wu, Yang, Zhang, Yifan, Wu, Yurong, Wang, Yuran, Zhang, Junkai, Cheng, Jian
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.17637
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909656007311360
author Wu, Yang
Zhang, Yifan
Wu, Yurong
Wang, Yuran
Zhang, Junkai
Cheng, Jian
author_facet Wu, Yang
Zhang, Yifan
Wu, Yurong
Wang, Yuran
Zhang, Junkai
Cheng, Jian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17637
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured Validation
Wu, Yang
Zhang, Yifan
Wu, Yurong
Wang, Yuran
Zhang, Junkai
Cheng, Jian
Computation and Language
Machine Learning
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.
title Step-Opt: Boosting Optimization Modeling in LLMs through Iterative Data Synthesis and Structured Validation
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2506.17637