SPADA: A Verifiable Test-Driven Agent for Controllable Parametric CAD Assembly Generation
Keyou Zheng, Xuyang Su, Jiewu Leng
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext fe414349-57c8-4236-bd25-c3bfdc97b9eaBuilds on24
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
- Reflexion: language agents with verbal reinforcement learningNoah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan et al.NeurIPS 2023 · 5,828 citations
- SWE-bench: Can Language Models Resolve Real-world Github Issues?Carlos E. Jimenez, John Yang, Alexander Wettig, Shunyu Yao et al.ICLR 2024 · 2,082 citations
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human PreferenceWei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios Nikolas Angelopoulos et al.ICML 2024 · 1,212 citations
- DeepCAD: A Deep Generative Network for Computer-Aided Design ModelsRundi Wu, Chang Xiao, Changxi ZhengICCV 2021 · 290 citations
Related papers
- Multi-Agent CAD Code GenerationYang Liu, Daxuan Ren, Yijie Ding, Jianmin Zheng et al.SIGGRAPH 2026
- Vitruvion: A Generative Model of Parametric CAD SketchesAri Seff, Wenda Zhou, Nick Richardson, Ryan P. AdamsICLR 2022 · 86 citations
- SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled CodebooksXiang Xu, Karl D. D. Willis, Joseph G. Lambourne, Chin-Yi Cheng et al.ICML 2022 · 126 citations
- Clarify Before You Draw: Proactive Agents for Robust Text-to-CAD GenerationBo Yuan, Zelin Zhao, Petr Molodyk, Bin Hu et al.ICML 2026 · 6 citations
- Learning Hierarchical and Geometry-Aware Graph Representations for Text-to-CADShengjie Gong, Wenjie Peng, Hongyuan Chen, Gangyu Zhang et al.ICLR 2026
