arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.12641cs.AI
收藏

STEP-LLM: 通过大型语言模型生成CAD STEP模型

STEP-LLM: Generating CAD STEP Models from Natural Language with Large Language Models

Northwestern University(西北大学)

Xiangyu Shi, Junyang Ding, Xu Zhao, Sinong Zhan, Payal Mohapatra, Daniel Quispe, Kojo Welbeck, Jian Cao, Wei Chen, Ping Guo, Qi Zhu

AI总结:

本文提出STEP-LLM,通过大型语言模型将自然语言转化为CAD STEP模型,采用图结构预处理和强化学习提升几何精度,验证了LLM驱动的STEP模型生成可行性。

摘要:

计算机辅助设计(CAD)对现代制造至关重要,但模型创建仍劳力密集且依赖专业知识。为使非专家能将直观设计意图转化为可制造的产物,近期基于大语言模型的文本到CAD研究聚焦于命令序列或脚本格式如CadQuery。然而,这些格式依赖内核且缺乏制造业的通用性。相比之下,产品数据交换标准(STEP,ISO 10303)文件是一种广泛采用的中性边界表示(B-rep)格式,直接兼容制造,但其图结构、交叉引用性质对自回归LLM提出了独特挑战。为此,我们编纂了约40,000个STEP-描述对的数据集,并引入了针对STEP图结构格式的新型预处理,包括基于深度优先搜索的重序列化,线性化交叉引用同时保持局部性和思维链(CoT)式结构注释,以引导全局一致性。我们整合了检索增强生成,以在监督微调中将预测与相关示例联系起来,并通过特定的Chamfer距离基于几何奖励的强化学习优化生成质量。实验表明,我们的STEP-LLM在几何保真度上优于Text2CAD基线,改进来自我们框架的多个阶段:RAG模块显著增强了完整性和可渲染性,DFS基于的重序列化增强了整体准确性,RL进一步减少了几何偏差。两者指标和视觉比较均确认STEP-LLM生成的形状比Text2CAD更精确。这些结果展示了通过自然语言驱动LLM生成STEP模型的可行性,展示了其在制造业CAD设计中的潜力。

英文摘要:

Computer-aided design (CAD) is vital to modern manufacturing, yet model creation remains labor-intensive and expertise-heavy. To enable non-experts to translate intuitive design intent into manufacturable artifacts, recent large language models-based text-to-CAD efforts focus on command sequences or script-based formats like CadQuery. However, these formats are kernel-dependent and lack universality for manufacturing. In contrast, the Standard for the Exchange of Product Data (STEP, ISO 10303) file is a widely adopted, neutral boundary representation (B-rep) format directly compatible with manufacturing, but its graph-structured, cross-referenced nature poses unique challenges for auto-regressive LLMs. To address this, we curate a dataset of ~40K STEP-caption pairs and introduce novel preprocessing tailored for the graph-structured format of STEP, including a depth-first search-based reserialization that linearizes cross-references while preserving locality and chain-of-thought(CoT)-style structural annotations that guide global coherence. We integrate retrieval-augmented generation to ground predictions in relevant examples for supervised fine-tuning, and refine generation quality through reinforcement learning with a specific Chamfer Distance-based geometric reward. Experiments demonstrate consistent gains of our STEP-LLM in geometric fidelity over the Text2CAD baseline, with improvements arising from multiple stages of our framework: the RAG module substantially enhances completeness and renderability, the DFS-based reserialization strengthens overall accuracy, and the RL further reduces geometric discrepancy. Both metrics and visual comparisons confirm that STEP-LLM generates shapes with higher fidelity than Text2CAD. These results show the feasibility of LLM-driven STEP model generation from natural language, showing its potential to democratize CAD design for manufacturing.

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。

↑