ASSEMCAD: Production-Ready CAD Assembly Generation from Natural Language

arXiv 2026 63 method, system, application

TLDR

AssemCAD generates production-ready CAD assemblies from natural language using an axiom-grounded framework with ports, mates, and B-Rep validation.

Reasoning

The paper introduces a novel framework for assembly-level CAD generation, addressing a gap in existing text-to-CAD methods. Its strengths include explicit engineering axioms and interpretable specifications, but the abstract lacks detailed experimental results or comparisons, limiting assessment of practical performance.

Read-first score

Read-first score 63, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 87.

Recency 8%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Methodology quality 25%

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

Topical relevance 42%

54.4

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%

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

Field roles

FrontierMethodology anchor

Rank sensitivity

Stability: volatile; rank range: 7.

Keyword Scores

text-to-CAD

computer-aided design

B-Rep

boundary representation

CAD generation

AI for CAD

generative CAD

parametric CAD

CAD program

neural CAD

CAD reconstruction

constructive solid geometry

CSG

sketch extrusion

image-to-CAD

point cloud to CAD

Deep Analysis

Innovations

Axiom-grounded Assembly Specification with typed parts, geometry-backed ports, executable mates, and engineering axioms, making assembly relations interpretable, reusable, and verifiable.
Port- and mate-based CAD assembly library that executes symbolic assembly relations via deterministic mate transformations and validates interfaces using B-Rep geometric evidence.
On-demand synthesis of reusable parametric component factories for both standard and open-world geometries, supporting production-ready assembly generation.

Methodology

AssemCAD first constructs an axiomatic Assembly Specification from natural language, then uses a port- and mate-based CAD assembly library to deterministically execute assembly relations and validate them with B-Rep geometry. It also supports on-demand synthesis of parametric component factories and is evaluated on the AssemBench benchmark against code-centric baselines.

Key Results

AssemCAD substantially improves assembly preservation and physical validity over code-centric CAD generation baselines, while generalizing across different foundation-model backbones.

Resources

Paper