SPADA: A Verifiable Test-Driven Agent for Controllable Parametric CAD Assembly Generation
Keyou Zheng, Xuyang Su, Jiewu Leng
摘要
Parametric CAD is widely used in mechanical and product engineering, but current generative models still have difficulty producing assemblies that are both editable at the parameter level and consistent with inter-part constraints. Methods that generate meshes or history-free B-rep can represent multi-part shape, but they often lack the program structure and constraint logic needed for reliable downstream edits; in contrast, code-based CAD generation offers direct parametric control, yet most published settings and evaluations focus on single-part solids rather than constrained assemblies. We introduce SPADA (Self-testing Parametric Assembly Design Agent), a test-driven agent that synthesizes assembly code together with deterministic verification tests, and uses these tests as an executable contract for controllable generation. SPADA runs an iterative compile-test-repair loop with multimodal feedback, checking both specification logic and physical feasibility through programmatic constraints. To support evaluation, we release SPADA-Bench-Verified, a human-validated benchmark of real-world code-centric assemblies paired with deterministic tests and engineering-style constraints. Experiments show that SPADA could produces complex assemblies while maintaining geometric fidelity, supporting test-driven agents as a concrete path toward reliable, controllable CAD generation.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper24
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning 等NeurIPS 2023 · 被引用 10,924 次
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan 等NeurIPS 2023 · 被引用 5,828 次
- SWE-bench: Can Language Models Resolve Real-world Github Issues?Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao 等ICLR 2024 · 被引用 2,082 次
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human PreferenceWei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos 等ICML 2024 · 被引用 1,212 次
- DeepCAD: A Deep Generative Network for Computer-Aided Design ModelsRundi Wu, Chang Xiao, Changxi ZhengICCV 2021 · 被引用 290 次
相关 Paper
- Multi-Agent CAD Code GenerationYang Liu, Daxuan Ren, Yijie Ding, Jianmin Zheng 等SIGGRAPH 2026
- Vitruvion: A Generative Model of Parametric CAD SketchesAri Seff, Wenda Zhou, Nick Richardson, Ryan P. AdamsICLR 2022 · 被引用 86 次
- SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled CodebooksXiang Xu, Karl D. D. Willis, Joseph G. Lambourne, Chin-Yi Cheng 等ICML 2022 · 被引用 126 次
- Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD GenerationBo Yuan, Zelin Zhao, Petr Molodyk, Bin Hu 等ICML 2026 · 被引用 6 次
- Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CADShengjie Gong, Wenjie Peng, Hongyuan Chen, Gangyu Zhang 等ICLR 2026
