GOPR-CAD：用图操作渐进推理生成更可靠的 Text-to-CAD 模型
GOPR-CAD: Graph-of-Operations Progressive Reasoning for CAD Generation
让 LLM 别再直接写 CAD 代码，只负责在封装操作上做决策，编译器兜底正确性。无需训练还能换模型。做机械设计或 CAD 自动化的工程师值得关注这个流水线思路和 MHCAD 基准。
论文提出 GOPR-CAD，一个基于 Graph-of-Operations 渐进推理的 agentic Text-to-CAD 流水线。语言模型作为决策智能体，在封装好的 CAD 操作上逐步构建可执行的操作图，再由确定性编译器转换成最终 CAD 模型，整个过程无需额外训练，可搭配不同语言模型使用。
现有 LLM 方法直接生成 CAD 程序，在长代码中同时协调几何、拓扑和尺寸约束时容易出错，生成的模型即使可执行、渲染正常，结构上也可能不正确。GOPR-CAD 把决策与执行分离，让模型只负责选操作、编译器保证正确性。
为评估结构保真度，作者构建了 MHCAD 基准，包含源自 Machinery's Handbook 的 300 个标准机械零件需求，支持无参考的 STEP/B-rep 评估。GOPR-CAD 在 MHCAD 上达到 82.7% Structural Yield，在外部 CADPrompt 子集上达到 87.2%。
GOPR-CAD: Graph-of-Operations Progressive Reasoning for CAD Generation
Generating accurate CAD models requires substantial engineering expertise and careful control of geometry, topology, and mechanical constraints. Text-to-CAD aims to simplify this process, but current LLM-based methods often generate CAD programs directly. Language models remain unreliable when producing long code while coordinating coupled geometric, topological, and dimensional constraints. Consequently, executable programs may still produce structurally incorrect models, which execution rate and rendered appearance may fail to reveal. To address these limitations, we propose GOPR-CAD, an agentic Text-to-CAD pipeline based on Graph-of-Operations Progressive Reasoning. A language model acts as a decision agent over encapsulated CAD operations and progressively constructs an executable operation graph, which a deterministic compiler converts into the final CAD model. This separation requires no additional training and supports different language models. To evaluate structural fidelity, we construct MHCAD, a benchmark of 300 standard mechanical part requirements derived from Machinery's Handbook. Their explicit structures enable reference-free STEP/B-rep evaluation. GOPR-CAD achieves 82.7% Structural Yield on MHCAD, and 87.2% Structural Yield on an external CADPrompt subset.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：GOPR-CAD、Text-to-CAD、CAD、Structural Yield，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Yitian Pang, Yifan Li, Xiaowei Yue, Li Zheng），经 AITOP 多维评分管线结构化提炼。