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

TL;DR

This paper introduces APF, a framework that uses fine-tuned large language models to automatically translate natural language design requirements into accurate, executable optimization models for high-cost simulation-driven design tasks.

Contribution

The paper presents a solver-independent, automated problem formulation framework that overcomes data scarcity by innovative data generation and fine-tuning of LLMs, improving formalization accuracy.

Findings

APF outperforms existing methods in formalizing requirements accurately.

APF generates higher quality optimization models for antenna design.

Experimental results show improved radiation efficiency curves.

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 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.