这篇论文用97个机械设计问题系统测试了7个模型，LLMForge的两种批评机制各有优劣，VLM批评做到100%水密网格但旋转体仍有缺陷。
本研究提出LLMForge，一个多模型文本到CAD框架，集成JSON模式验证、解析特征评分、网格合成和多轮迭代优化。在包含97个工程设计问题的基准上评估了DeepSeek-V3.2、Qwen3-235B-A22B等7个基础模型。IterTracer批评机制使用Phong着色光线追踪和分析视觉指标（轮廓IoU、孔可见性、边缘间隙等），四个最优模型平均得分在0.885-0.890之间，网格成功率98.97%。IterVision采用Qwen2.5-VL-72B作为VLM语义批评，实现100%水密网格生成，但在旋转对称几何体（如圆柱）上视觉与语义评分存在分歧。
Foundation Models for Automatic CAD Generation
Recent advances in Large Language Models (LLMs) and Vision-Language Models (VLMs) enable the automatic generation of parametric 3D designs from natural-language specifications. This chapter presents an empirical study of foundation models for automatic Computer-Aided Design (CAD) generation of mechanical parts, using a unified evaluation pipeline and a curated benchmark of 97 engineering design problems. We introduce LLMForge, a multi-model text-to-CAD framework integrating JSON-schema validation, analytic feature scoring, mesh synthesis, and multi-round iterative refinement, studied under two critique regimes. IterTracer uses a Phong-shaded ray-trace renderer with analytic visual metrics (silhouette IoU, hole visibility, edge clearance, aspect-ratio conformance) for lightweight geometry-aware feedback across rounds. IterVision replaces the analytic scorer with a VLM semantic critic (Qwen2.5-VL-72B) that evaluates rendered views via chain-of-thought visual reasoning, assessing spatial coherence and design intent. On a benchmark spanning four canonical geometry families (plates with holes and bolt circles, multi-feature boxes, flanged cylinders, and L-brackets), we evaluate seven foundation models: DeepSeek-V3.2, Qwen3-235B-A22B, Llama-3.3-70B, Gemma-3-27B, GLM-4.5, MiniMax-M2.1, and INTELLECT. Under IterTracer, the four highest-ranked models form a tight cluster (overall mean in [0.885, 0.890]) with 98.97% mesh success, showing that compact instruction-tuned models can match substantially larger systems. VLM-based critique in IterVision yields 100% watertight mesh generation on the leading model while surfacing systematic difficulty on rotationally symmetric geometries such as cylinders, where visual and semantic scoring diverge most. We discuss benchmark design, failure modes, CAD-oriented prompting, and implications for industrial workflows and scalable automated mechanical design.