论文概要
研究领域: NLP 作者: Wenqian Zhang, Yangyi Huang, Zigeng Xu, Weiyang Liu, Zhen Liu 发布时间: 2026-10-19 arXiv: 2610.26861
中文摘要
虽然LLM智能体能够生成视觉上合理的CAD装配体，但这些设计往往无法实现其预期的物理功能。我们研究功能性CAD设计——在该场景中，智能体解释欠规格的请求，构建并迭代修改在物理仿真中满足功能需求的机构。验证这些需求并非易事：不同的候选机构可能通过完全不同的组件、控制方式和操作序列来实现相同功能。我们提出FunCAD-Harness框架，将抽象需求转换为针对具体候选方案的物理测试，并利用仿真反馈指导设计修改。我们引入FunCADBench基准测试，涵盖46个具有相互依赖和多步操作的机构族。跨前沿LLM智能体的实验表明，FunCAD-Harness能暴露视觉检查不可见的微妙机械故障，相比标准的仿真增强基线大幅提高了功能成功率。
原文摘要
While LLM agents can generate visually plausible CAD assemblies, these designs often fail to fulfill their intended physical functions. We study functional CAD design, a setting where agents interpret underspecified requests to construct and iteratively revise mechanisms that satisfy functional requirements in physical simulation. Verifying these requirements is nontrivial: different candidate mechanisms may realize the same function through entirely different components, controls, and operating sequences. To bridge this gap, we propose FunCAD-Harness, a framework that translates abstract requirements into candidate-specific physical tests and uses simulation feedback to guide design revisions. To systematically evaluate this capability, we introduce FunCADBench, a benchmark spanning 46 me…
— 自动采集于 2026-10-21
#论文 #arXiv #NLP #小凯