ACL Findings2026
Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Design
Yuchen Li, Handing Wang, Bing Xue, Mengjie Zhang, Yaochu Jin
Abstract
In the high-cost simulation-driven design domain, translating ambiguous design requirements into a mathematical optimization formulation is a bottleneck for optimizing product performance. This process is time-consuming and heavily reliant on expert knowledge. While large language models (LLMs) offer potential for automating this task, existing approaches either suffer from poor formalization that fails to accurately align with the design intent or rely on solver feedback for data filtering, which is unavailable due to the high simulation costs. To address this challenge, we propose automated problem formulation (APF), a solverindependent framework that utilizes LLMs to convert engineers' natural language requirements into executable optimization models. The core of this framework is an innovative pipeline for automatically generating highquality data, which overcomes the difficulty of constructing suitable fine-tuning datasets in the absence of high-cost solver feedback with the help of data generation and test instance annotation. The generated high-quality dataset is used to perform supervised fine-tuning on LLMs, significantly enhancing their ability to generate accurate and executable optimization problem formulations. Experimental results on antenna design demonstrate that APF significantly outperforms the existing methods in both the accuracy of requirement formalization and the quality of resulting radiation efficiency curves in meeting the design goals.
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.
Lineage
- Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling cites STaR: Bootstrapping Reasoning With Reasoning
- Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling cites OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models
- Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling cites WizardCoder: Empowering Code Large Language Models with Evol-Instruct
Builds on11
- STaR: Bootstrapping Reasoning With ReasoningEric Zelikman, Yuhuai Wu, Jesse Mu, Noah D. GoodmanNeurIPS 2022 · 1,126 citations
- WizardCoder: Empowering Code Large Language Models with Evol-InstructZiyang Luo, Can Xu, Pu Zhao, Qingfeng Sun et al.ICLR 2024 · 945 citations
- On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A SurveyLin Long, Rui Wang, Ruixuan Xiao, Junbo Zhao et al.ACL Findings 2024 · 131 citations
- OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language ModelsAli AhmadiTeshnizi, Wenzhi Gao, Madeleine UdellICML 2024 · 77 citations
- Solver-Informed RL: Grounding Large Language Models for Authentic Optimization ModelingYitian Chen, Jingfan Xia, Siyu Shao, Dongdong Ge et al.NeurIPS 2025 · 54 citations
Related papers
- Autoformulation of Mathematical Optimization Models Using LLMsNicolás Astorga, Tennison Liu, Yuanzhang Xiao, Mihaela van der SchaarICML 2025
- Automated CAD Modeling Sequence Generation from Text Descriptions via Transformer-Based Large Language ModelsJianxing Liao, Junyan Xu, Yatao Sun, Maowen Tang et al.ACL 2025 · 8 citations
- Artisan: Automated Operational Amplifier Design via Domain-specific Large Language ModelZihao Chen, Jiangli Huang, Yiting Liu, Fan Yang et al.DAC 2024 · 30 citations
- Large Language Models as OptimizersChengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu et al.ICLR 2024 · 817 citations
- VeriSimpl: Robust Optimization Modeling from Natural Language using Simplification-based VerificationSumaya Abdul Rahman, Seckhen Cuellar, Ghani Raissov, Mohammad RazaICML 2026 · 1 citation
