CADIR：一种用于智能体CAD生成的跨后端可编辑中间表示
CADIR: A Cross-Backend Editable Intermediate Representation for Agentic CAD Generation
浏览论文内容
中文总结 AI 辅助
本研究提出CADIR跨后端可编辑中间表示，结合几何签名匹配与构造图检索，解决现有CAD生成方法的跨系统编辑与建模历史保留问题，实验验证其几何保真度与可靠性优于现有方案。
中文摘要 AI 辅助
大型语言模型已能够根据自然语言描述或图像生成可执行的计算机辅助设计（CAD）程序。然而，现有方法将建模过程表示为特定后端的顺序脚本（存在隐式依赖）或静态几何，难以在不同CAD系统间同时保留构造历史、稳定拓扑参考和特征级可编辑性。我们提出CADIR，一种用于CAD生成和跨后端编辑的智能体友好型可执行中间表示。CADIR基于OCCT几何内核通过OCP构建，提供显式、组合式建模操作和细粒度执行诊断。程序执行期间，CADIR在构造图中记录建模操作、参数依赖、约束及拓扑选择。为实现可靠的跨后端重构，我们引入几何签名匹配技术，尽管存在参数变化和后端差异，仍能识别对应边和面，使适配器可在FreeCAD、SolidWorks和Fusion 360中重构原生可编辑特征历史。基于该表示，我们进一步提出用于文本和图像查询的构造图检索方法，支持全图和子图检索，使智能体可利用完整模型和建模子结构。大量实验表明，CADIR比现有CAD表示实现更高的几何保真度和执行可靠性；构造图检索进一步提升模型生成质量；跨后端编辑支持在多个CAD环境中实现可靠的模型重构及重构后编辑。
英文摘要
Large language models have made it possible to generate executable computer-aided design (CAD) programs from natural-language descriptions or images. However, existing methods represent modeling processes as backend-specific sequential scripts with implicit dependencies or as static geometry, making it difficult to simultaneously preserve construction history, stable topological references, and feature-level editability across different CAD systems. We present CADIR, an agent-friendly executable intermediate representation for CAD generation and cross-backend editing. Built on the OCCT geometry kernel via OCP, CADIR provides explicit, compositional modeling operations and fine-grained execution diagnostics. During program execution, CADIR records modeling operations, parameter dependencies, constraints, and topology selections in a construction graph. To enable reliable cross-backend reconstruction, we introduce Geometric Signature Matching, which identifies corresponding edges and faces despite parameter changes and backend differences, allowing adapters to reconstruct native editable feature histories in FreeCAD, SolidWorks, and Fusion 360. Building on this representation, we further propose a construction-graph retrieval method for text and image queries that supports both full-graph and subgraph retrieval, enabling agents to leverage complete models and modeling substructures. Extensive experiments demonstrate that CADIR achieves higher geometric fidelity and execution reliability than existing CAD representations, that construction-graph retrieval further improves model generation quality, and that cross-backend editing enables reliable model reconstruction and post-reconstruction editing across multiple CAD environments.
