Awesome AI4CAD Hub Papers · Datasets · Projects
← Back to papers

From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation

arXiv 2025 63.1 method

TLDR

Proposes CAD-RL, a multimodal Chain-of-Thought reinforcement learning framework for precise CAD code generation from natural language, with a new real-world dataset ExeCAD.

Reasoning

The paper introduces a novel combination of CoT reasoning and RL with task-specific rewards for CAD code generation, supported by a new dataset of real-world CAD examples. Strengths include clear methodology and optimization strategies; weaknesses are that the abstract is cut off, limiting full assessment of results and limitations.

Read-first score

Read-first score 63.1, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 84.

Methodology quality 25%
90

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=benchmark,dataset,evaluation,experiment,metric

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Topical relevance 42%
52.5

Uses existing LLM keyword relevance scores normalized to 0-100. AI for CAD,computer-aided design,neural CAD,generative CAD,parametric CAD,B-Rep,boundary representation,constructive solid geometry,CSG,sketch extrusion,CAD generation,CAD reconstruction,text-to-CAD,image-to-CAD,point cloud to CAD,CAD program

Reproducibility 25%
46

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code,dataset

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 8.

Keyword Scores

AI for CAD
9
computer-aided design
9
parametric CAD
9
CAD generation
9
text-to-CAD
9
generative CAD
8
CAD program
8
neural CAD
7
constructive solid geometry
3
CSG
3
B-Rep
2
boundary representation
2
sketch extrusion
2
CAD reconstruction
2
image-to-CAD
1
point cloud to CAD
1

Deep Analysis

Innovations

  • Multimodal Chain-of-Thought guided reinforcement learning post-training framework for CAD code generation
  • Three task-specific rewards: executability reward, geometric accuracy reward, and external evaluation reward
  • Three optimization strategies for stable policy learning: Trust Region Stretch, Precision Token Loss, and Overlong Filtering
  • ExeCAD dataset: 16,540 real-world CAD examples with paired natural language, structured descriptions, executable CADQuery scripts, and rendered 3D models

Methodology

CAD-RL combines Chain-of-Thought cold start with goal-driven reinforcement learning post-training using three rewards (executability, geometric accuracy, external evaluation). To handle sparse and high-variance rewards, it introduces Trust Region Stretch, Precision Token Loss, and Overlong Filtering. The ExeCAD dataset supports training and benchmarking.

Key Results

CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability over existing vision-language models.

Tags