Lune

EMNLP Findings2025

Training LLMs for Optimization Modeling via Iterative Data Synthesis and Structured Validation

Yang Wu, Yifan Zhang, Yurong Wu, Yuran Wang, Junkai Zhang, Jian Cheng

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 stateof-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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Opt-Miner: Empowering Information-Seeking Agent with Tree-Guided Data Synthesis for Optimization Modeling cites Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verification
  • Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verification cites Opt-Miner: Empowering Information-Seeking Agent with Tree-Guided Data Synthesis for Optimization Modeling
  • Magicoder: Empowering Code Generation with OSS-Instruct cites Self-Instruct: Aligning Language Models with Self-Generated Instructions
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side VerificationHaoyang Liu, Jie Wang, Boxuan Niu, Xiongwei Han et al.ICML 2026 · 4 citations
  2. Opt-Miner: Empowering Information-Seeking Agent with Tree-Guided Data Synthesis for Optimization ModelingHaoyang Liu, Yuyang Cai, Jie Wang, Xiongwei Han et al.ICML 2026

Builds on8

  1. LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
  2. Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
  3. WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex InstructionsCan Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng et al.ICLR 2024 · 1,206 citations
  4. Self-Instruct: Aligning Language Models with Self-Generated InstructionsYizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu et al.ACL 2023 · 540 citations
  5. Magicoder: Empowering Code Generation with OSS-InstructYuxiang Wei, Zhe Wang, Jiawei Liu, Yifeng Ding et al.ICML 2024 · 246 citations

Related papers

  1. Large Language Models as OptimizersChengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu et al.ICLR 2024 · 817 citations
  2. OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement LearningZezhen Ding, Zhen Tan, Jiheng Zhang, Tianlong ChenAAAI 2026
  3. MAmmoTH2: Scaling Instructions from the WebXiang Yue, Tianyu Zheng, Ge Zhang, Wenhu ChenNeurIPS 2024 · 176 citations
  4. Evaluating LLM Reasoning in the Operations Research Domain with ORQAMahdi Mostajabdaveh, Timothy Tin Long Yu, Samarendra Chandan Bindu Dash, Rindra Ramamonjison et al.AAAI 2025 · 1 citation
  5. OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization ModelingHaoyang Liu, Jie Wang, Yuyang Cai, Xiongwei Han et al.NeurIPS 2025 · 33 citations
Dusk over the sea between two cliffs drawn in fine vertical lines