用大模型解决工程系统模块化问题，30次迭代逼近最优解。
Design Structure Matrix Modularization with Large Language Models
- 基于大模型的结构化优化方法，无需专用代码即可快速求解。
- 在五种案例中达到接近参考结果的模块化质量。
- 发现领域知识在复杂场景下反而降低效果，提出语义对齐假说。
设计结构矩阵（DSM）模块化是工程设计中的核心组合优化问题，旨在将系统元素划分为高内聚模块。传统方法将其视为纯图优化，缺乏对系统工程上下文的利用。本文基于前期大模型用于DSM排序的研究，将方法扩展至五个案例和三种基础大模型。所提方法在30次迭代内即达到近参考水平的模块化质量，且无需专门优化代码。反直觉的是，领域知识在排序中有益，但在更复杂的DSM上反而持续损害性能。我们归因于大模型的功能先验与纯粹结构优化目标之间的语义错位，并提出语义对齐假说作为可验证的条件，以判断知识在大模型中的有效性。消融实验识别出最有效的输入表示、目标设定方式及解池设计，为大模型在工程优化中的实际部署提供实用指导。
原文摘要 · Abstract (English)
Design Structure Matrix (DSM) modularization, the task of partitioning system elements into cohesive modules, is a fundamental combinatorial challenge in engineering design. Traditional methods treat modularization as a pure graph optimization, without access to the engineering context embedded in the system. Building on prior work on LLM-based combinatorial optimization for DSM sequencing, this paper extends the method to modularization across five cases and three backbone LLMs. Our method achieves near-reference quality within 30 iterations without requiring specialized optimization code. Counterintuitively, domain knowledge, beneficial in sequencing, consistently impairs performance on more complex DSMs. We attribute this to semantic misalignment between the LLM's functional priors and the purely structural optimization objective, and propose the semantic-alignment hypothesis as a testable condition governing knowledge effectiveness with LLMs. Ablation studies identify the most effective input representation, objective formulation, and solution pool design for practical deployment. These findings offer practical guidance for deploying LLMs in engineering design optimization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。