Parametric CAD Modeling

Follow this topic Ask about this topic

Parametric CAD modeling studies how to build and change 3D designs through ordered operations, dimensions, geometric constraints, and boundary representations (B-reps), so models remain editable and usable in engineering workflows. Methods include autoregressive and diffusion models for CAD programs, graph-based representations of geometry and design structure, and language-model agents that create or revise code using CAD-kernel execution and geometric feedback. Systems are evaluated on tasks such as generating designs from text or images, reconstructing programs from meshes or drawings, editing construction histories, and assembling parts, with measures of execution, geometric fidelity, constraint satisfaction, and engineering behavior. Although iterative tool use and richer datasets are improving results, models still struggle to preserve design intent, precise dimensions, topology, and editability, especially on complex or unfamiliar designs.

Latest papers

82 papers9 papers in the last four weeks, down 18% on the four weeks before. 0.1% of all new papers.

CAD-WAM: Anticipating Geometry for Text-to-CAD Generation
Oct 29, 2026Zhengyang Li, Weijie Zheng, Yuxin Cui +3Text-to-CAD Generation Parametric CAD Modeling
University of Science and Technology of China · Nanyang Technological University
CADonatello: Towards Real-World Multi-Part 3D CAD Reconstruction
Oct 24, 2026Ahmet Serdar Karadeniz, Dimitrios Mallis, Parsa Akbari Chianeh +33D Reconstruction Parametric CAD Modeling
SnT, University of Luxembourg · Artec 3D
Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning
Oct 11, 2026Qingwang Zhang, Jiahao Li, Xiangdong ZhouParametric CAD Modeling Text-to-CAD Generation
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China
Automatic assembly modeling through attention-based assembly feature mate prediction and assembly feature pattern recognition
Oct 10, 2026Ziheng Dai, Wanbin Pan, Zhihong Tang +1Parametric CAD Modeling
State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou, 310058, Zhejiang, People’s Republic of China · School of Media and Design, Hangzhou Dianzi University, Hangzhou, 310001, Zhejiang, People’s Republic of China
Look Where You Can: Active View Selection for CAD Reconstruction under Occlusion
Oct 8, 2026Kartik Bali, Mahish Guru, Yiderigun Borjigin +3Active View Selection 3D Reconstruction
Helmholtz-Zentrum Hereon · Leuphana Universität Lüneburg · Universität des Saarlandes +1
CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use
Oct 6, 2026Gennadiy Savrasov, Maksim Elistratov, Nikita Gavrilov +7Parametric CAD Modeling 3D Reconstruction
Lomonosov Moscow State University · Innopolis University · FusionBrain Lab
CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning
Oct 3, 2026Keyang Lu, Zhifei Yang, Tianao Dong +3Parametric CAD Modeling Single-View 3D Reconstruction
Peking University · Shenzhen Loop Area Institute · Beijing Normal University
UniBRep: Learning Unified Geometry and Topology for Image-conditioned B-Rep Generation
Oct 2, 2026Haiyang Ying, Allen Tu, Jiaye Wu +2Parametric CAD Modeling Single-View 3D Reconstruction
University of Maryland, College Park, Maryland, USA · Amazon, Bellevue, Washington, USA
StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search
Oct 1, 2026Ghadi Nehme, Faez AhmedParametric CAD Modeling Program Synthesis
Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge, MA 02139
ConCAD: Constraint-Aware Image-to-CAD Generation with Dual-Granularity Rewards
Sep 28, 2026Chenxi Zhai, Xi Cheng, Hang Cheng +5Constrained Generative Modeling 3D Asset Generation
Tsinghua University, Shenzhen International Graduate School
DIP-CAD: A Design-Intent-Preserving Agent Harness for Parametric CAD Modeling
Sep 19, 2026Xi Cheng, Chenxi Zhai, Hang Cheng +3Parametric CAD Modeling Text-to-CAD Generation
Division of Advanced Manufacturing, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, 518055, China · Department of Mechanical Engineering, Tsinghua University, Beijing, 100084, China
VGGT-CAD: Reconstructing Parametric CAD 3D Model with Geometric Grounding
Sep 18, 2026Chunan Yu, Tianrun Chen, Fu Shen +3Parametric CAD Modeling Multi-View 3D Reconstruction
School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China · KOKONI3D, Moxin (Huzhou) Technology Co., Ltd., China · Nanjing Institute of Agricultural Mechanization, Ministry of Agriculture and Rural Affairs, Nanjing 210014, China
ReliCAD: From Uncertain LLM Generation to Reliable Parametric CAD Modeling
Sep 16, 2026Peng Zheng, Xintong Dong, Chuanyang Li +5Parametric CAD Modeling Text-to-CAD Generation
University of Science and Technology of China, Hefei, Anhui 230026, China
CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design
Sep 14, 2026Zihan Dong, Yuanzhe Liu, Zhiyuan Ma +4Computer-Use Agent Benchmarks Long-Horizon Agent Tasks
Georgia Institute of Technology · North Carolina State University · Marquette University +3
CGGT: Curve-Grounded Geometry Transformer for 3D Parametric Curve Reconstruction
Sep 13, 2026Zhirui Gao, Renjiao Yi, Yunfan Ye +43D Reconstruction Parametric CAD Modeling
National University of Defense Technology, China · Hunan University, China · Shenzhen University, Shenzhen, China +1
Language-Augmented Semantic Priors for B-Spline Surface Fitting
Sep 10, 2026Yunzhong Lou, Yusheng Luo, Jiahao Li +2Large Language Model-Guided Optimization Parametric CAD Modeling
College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China
CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification
Sep 7, 2026Yali Du, Hui Sun, San-Zhuo Xi +1Parametric CAD Modeling Text-to-CAD Generation
National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, China
LLM-Aided Design for Manufacturing: A Multi-Agent System for Intent-Preserving Redesign of CAD for Improved Manufacturability
Sep 3, 2026Kojo Welbeck, Xiangyu Shi, Zahra Sadeghi +2Multi-Agent LLM Systems Parametric CAD Modeling
Department of Mechanical Engineering, Northwestern University, Evanston, USA · Department of Electrical and Computer Engineering, Northwestern University, Evanston, USA
VisCAD: A Foundation Model Suite with Multimodal Industrial CAD Intelligence
Sep 3, 2026Guanlin Li, Zhichao Huang, Huimu Yu +9Part-Level 3D Generation Parametric CAD Modeling
RealCADBench: Benchmarking Parametric CAD Modeling from Industrial Design Intents
Sep 3, 2026Guanlin Li, Zhichao Huang, Huimu Yu +8Benchmark Design Parametric CAD Modeling
RealCAD: Towards Real-World Image-to-CAD Reconstruction under Domain Shift and Parameter Bias
Aug 31, 2026Yihe Sun, Ziyu Lu, Kaihua Tang +1Synthetic-to-Real Domain Adaptation Parametric CAD Modeling
Tongji University
AgenticCADedit: A Stateful, Tool-Mediated Agentic Approach to Multimodal 3D CAD Editing
Aug 28, 2026Saptarshi Neil Sinha, Mika Silvan Goschke, Paul Julius Kühn +23D Shape Editing Multimodal Tool Use
Fraunhofer IGD, Darmstadt, Germany · TU Darmstadt, Darmstadt, Germany · Delft University of Technology, Delft, Netherlands
Procedura: Agentic 3D Modeling with Procedural Control
Aug 26, 2026Youtian Lin, Yikang Yang, Zhanpeng Hu +5Procedural 3D Generation Text-to-3D Generation
Nanjing University · Envision
ExpConCAD: Experience-Guided Text-to-CAD Generation from Shape Descriptions with Implicit Spatial Constraints
Aug 25, 2026Jingyao Liu, Jinkang Tang, Chen Huang +2Text-to-CAD Generation Parametric CAD Modeling
College of Computer Science, Sichuan University · Engineering Research Center of Machine Learning and Industry Intelligence, Ministry of Education, China · Institute of Data Science, National University of Singapore
IterCAD: Iterative Program Repair for CAD Code Generation from Orthographic Views
Aug 25, 2026Yuchuan Wu, Ke Niu, Haiyang Yu +3Parametric CAD Modeling Execution-Guided Code Generation
Fudan University Shanghai, China
MIRAGE-CAD: Construction-Mediated Multimodal Generation of Executable CAD Programs
Aug 24, 2026Jizong ZhanParametric CAD Modeling Text-to-CAD Generation
Test-Time Scaling for CAD Generation via Verifier-Free Consensus Selection
Aug 10, 2026Aaron Haag, Altay Kacan, Bertram Fuchs +1Parametric CAD Modeling Test-Time Scaling
Siemens AG, Foundational Technologies, Munich, Germany
CADEngBench: It Looks Like CAD, but Does It Work? Evaluating Parametric Design, Assembly Reasoning, and Physics Simulation
Aug 10, 2026Harmanjot Singh, Abhra Dubey, Jorge Alejandro Amador HerreraBenchmark Construction Parametric CAD Modeling
Mohamed Bin Zayed University of Artificial Intelligence · Abu Dhabi, UAE
RA-CAD: Learning Post-Execution Critique for State-Aware Text-to-CAD Generation
Aug 6, 2026Shuhao Yan, Changhao He, Peng Hu +1RL for Code Generation Code Generation
College of Computer Science, Sichuan University, Chengdu, China · School of Artificial Intelligence, Sichuan University, Chengdu, China · National Key Laboratory of Fundamental Algorithms and Models for Engineering Numerical Simulation, Sichuan University, Chengdu, China
OmniMech: All-in-one Multimodal Mechanical Benchmark for 3D Reconstruction
Aug 6, 2026Taiting Lu, Runze Liu, Ziwei Dong +18Manufacturing 3D Reconstruction
Pennsylvania State University · Independent Researcher · Shanghai Jiao Tong University +2

Oct 29, 2026J/K move · Enter open · S save

CAD-WAM: Anticipating Geometry for Text-to-CAD Generation

Zhengyang Li, Weijie Zheng, Yuxin Cui, Sijie Wang+2

University of Science and Technology of China · Nanyang Technological University

Text-to-CAD Generation Parametric CAD Modeling World Models

Open paper AskPDF arXiv

Generating editable computer-aided design (CAD) models from text requires selecting operations that produce the intended changes to the geometry constructed so far. An incorrect operation can compromise subsequent steps, making reliable multi-step generation challenging. Existing methods based on large language models (LLMs) primarily learn to predict commands, without explicit supervision of the geometric states those commands should produce. Inspired by world-action models, we introduce CAD-WAM, which couples geometry-conditioned action generation with next-state prediction. We define complete modeling operations as actions in a CAD domain-specific language (DSL) and encode surface point clouds of intermediate solids into compact latent states using a pretrained variational autoencoder. An LLM backbone generates the next action from the target description and current geometric state, while an auxiliary head on the same backbone predicts the next state to provide geometric supervision during training. We construct step-wise training trajectories from parametric CAD models in the DeepCAD dataset, pairing each trajectory with an expert-level textual description. At inference, each generated action is executed by a CAD kernel, and the resulting solid is re-encoded to inform the next decision. On the DeepCAD test set, CAD-WAM outperforms the task-specific baselines in geometric accuracy and output validity, with larger gains on models requiring more operations, and produces more accurate geometry than general-purpose LLMs prompted with the same DSL. Ablations further show that next-state supervision reduces mean Chamfer distance by 13.2% relative to an otherwise identical model trained only to predict actions. Code is available at https://github.com/Lzy-1037/CAD-WAM.