ReliCAD：从不确定的大语言模型生成到可靠的参数化CAD建模

中文摘要 AI 辅助

大型语言模型在自然语言驱动的参数化CAD建模方面显示出相当大的潜力。然而，其概率生成与CAD建模的确定性要求之间存在根本性矛盾，导致在可靠性、设计意图保留和几何有效性方面存在局限。现有方法通常依赖大规模标注数据集，缺乏对设计意图的显式建模，并且未充分利用CAD内核的确定性能力。为解决这些局限，我们提出ReliCAD，一个将不确定的大语言模型生成转化为可靠参数化CAD建模的统一框架。通过显式的设计意图建模，ReliCAD将用户需求转换为结构化的设计规范，并显式建模几何关系、拓扑依赖和特征构建顺序。随后，它生成约束感知的参数化指令，并通过Agent-ready API调用CAD内核来执行几何构建和约束求解。ReliCAD进一步记录运行时证据，并采用验证-反馈机制来评估生成模型与设计规范之间的一致性，从而实现错误定位和迭代修复。在公开的HistCAD生成数据集和我们构建的多粒度CAD编辑数据集上的实验表明，ReliCAD显著优于基线方法，实现了99.8%的有效率和0.8753的IoU。ReliCAD为自然语言交互式CAD建模提供了一种可验证、可修复且可泛化的方法。

英文摘要

Large language models have shown considerable potential for natural-language-driven parametric CAD modeling. However, a fundamental contradiction exists between their probabilistic generation and the deterministic requirements of CAD modeling, resulting in limitations in reliability, design-intent preservation, and geometric validity. Existing methods typically rely on large-scale annotated datasets, lack explicit modeling of design intent, and underutilize the deterministic capabilities of CAD kernels. To address these limitations, we propose ReliCAD, a unified framework that transforms uncertain LLM generation into reliable parametric CAD modeling. Through explicit design-intent modeling, ReliCAD converts user requirements into structured design specifications and explicitly models geometric relations, topological dependencies, and feature construction order. It then generates constraint-aware parametric instructions and invokes the CAD kernel through an Agent-ready API to perform geometric construction and constraint solving. ReliCAD further records runtime evidence and employs a verification-feedback mechanism to assess consistency between the generated model and the design specifications, enabling error localization and iterative repair. Experiments on the public HistCAD generation dataset and our multi-granularity CAD editing dataset demonstrate that ReliCAD significantly outperforms baseline methods, achieving 99.8\% validity rate and 0.8753 IoU. ReliCAD provides a verifiable, repairable, and generalizable approach to natural-language-interactive CAD modeling.

发表机构

• University of Science and Technology of China（中国科学技术大学）

机构由 AI 辅助整理，请以论文原文为准。