让AI生成的CAD模型修复更可靠，通过追踪错误和修复过程提升成功率。
TraceCAD: Trace-Guided Repair for Agentic CAD Generation
- 构建可持久化的错误追踪系统，关联需求、步骤与修复结果。
- 在200个模型测试中保持高几何精度，修复成功率接近翻倍。
- 适合需要稳定生成高质量3D模型的研发团队使用。
基于大语言模型的CAD代理能生成可执行的参数化程序，但其纠错循环会丢失满足的需求、故障操作及先前修复的证据。我们提出TraceCAD，一个恢复层，将请求特征、建模步骤、失败证据和候选结果作为持久状态进行关联。TraceCAD诊断可能出错的操作，在其依赖区域中搜索有限修改，通过执行与保留检查验证候选方案，并将成功与失败的修复结果存入可复用的技能记忆库。在基于DeepCAD的基准测试中，包含200个模型的消融实验与1000个模型的对比实验表明，TraceCAD在交并比（IoU）、Chamfer距离和Hausdorff距离上表现优异。移除持久状态使恢复得分几乎减半；移除局部搜索使几何退化超过两倍，代码代理调用次数翻倍。在不重叠训练模型上初始化技能库可进一步降低重试次数、令牌消耗与延迟。结果表明，持久化、局部化且可复用的恢复机制显著提升了最终CAD质量和修复可靠性。
原文摘要 · Abstract (English)
LLM-based CAD agents produce executable parametric programs, but their correction loops may lose evidence about satisfied requirements, faulty operations, and prior repairs. We introduce TraceCAD, a recovery layer that links requested features, modeling steps, failure evidence, and candidate outcomes as persistent state. TraceCAD diagnoses likely faulty operations, searches bounded edits in their dependency regions, validates candidates through execution and preservation checks, and retains successful and failed repair outcomes in reusable skill memory. On DeepCAD-derived benchmarks with 200-model ablations and a 1K-model comparison, TraceCAD achieves competitive geometric quality in terms of IoU, Chamfer distance, and Hausdorff distance. Removing persistent state nearly halves recovery score; removing localized search more than doubles geometric regression and doubles code-agent invocations. Initializing the skill store on disjoint training models further reduces retries, token cost, and latency. These results demonstrate that persistent, localized, and reusable recovery improves final CAD quality and repair reliability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。