arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.18682cs.CLcs.SE
收藏

通过LLM实现的无求解器依赖的自动问题建模

Solver-Independent Automated Problem Formulation via LLMs for High-Cost Simulation-Driven Design

School of Artificial Intelligence, Xidian University(西安电子科技大学人工智能学院);School of Engineering and Computer Science, Victoria University of Wellington(惠灵顿维多利亚大学工程与计算机科学学院);School of Engineering, Westlake University(西湖大学工学院)

Yuchen Li, Handing Wang, Bing Xue, Mengjie Zhang, Yaochu Jin

AI总结:

本文提出APF框架,利用LLM将工程师的自然语言需求转化为可执行的优化模型,提升高成本仿真驱动设计中问题建模的准确性和效率。

摘要:

在高成本仿真驱动设计领域,将模糊的设计需求转化为数学优化形式是优化产品性能的关键瓶颈。这一过程耗时且高度依赖专家知识。尽管大语言模型(LLMs)有潜力自动化此任务,但现有方法要么在形式化方面表现不佳,无法准确对齐设计意图,要么依赖求解器反馈进行数据过滤,这在高仿真成本情况下不可行。为解决这一挑战,我们提出了APF,一个通过LLM实现无求解器依赖的自动问题建模框架,旨在将工程师的自然语言需求自动转换为可执行的优化模型。该框架的核心是一个创新的管道,用于自动生成高质量数据,通过数据生成和测试实例注释,在缺乏高成本求解器反馈的情况下克服了构建合适微调数据集的困难。生成的高质量数据集用于对LLM进行监督微调,显著增强了其生成准确且可执行的优化问题形式化的能力。在天线设计实验中,APF在要求形式化的准确性及最终辐射效率曲线的质量方面均显著优于现有方法。

英文摘要:

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 APF, a framework for solver-independent, automated problem formulation via LLMs designed to automatically convert engineers' natural language requirements into executable optimization models. The core of this framework is an innovative pipeline for automatically generating high-quality 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑