# CadQuery

CadQuery is a Python library for building parametric 3D CAD models programmatically.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## PhyCAD: Physics-Aware Text-to-CAD Generation via Hierarchical Reinforcement Learning

DevFeed: [PhyCAD: Physics-Aware Text-to-CAD Generation via Hierarchical Reinforcement Learning](<https://devfeed.tech/articles/phycad-physics-aware-text-to-cad-generation-via-hierarchical-reinforcement-learning-124674.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09401>)

Author: Yuxin Cui, Weijie Zheng, Zhengyang Li, Han Wang, Wenjie Feng, Qiyu Kang

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [grpo](<https://devfeed.tech/topics/grpo.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [CadQuery](<https://devfeed.tech/topics/cadquery.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [rlvr](<https://devfeed.tech/topics/rlvr.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [automated](<https://devfeed.tech/tags/automated.md>), [cad](<https://devfeed.tech/tags/cad.md>), [cadquery](<https://devfeed.tech/tags/cadquery.md>), [cae](<https://devfeed.tech/tags/cae.md>), [computer-aided-design](<https://devfeed.tech/tags/computer-aided-design.md>), [constraint-satisfaction](<https://devfeed.tech/tags/constraint-satisfaction.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [group-relative-policy-optimization](<https://devfeed.tech/tags/group-relative-policy-optimization.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [learning](<https://devfeed.tech/tags/learning.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [physics](<https://devfeed.tech/tags/physics.md>), [reinforcement-learning](<https://devfeed.tech/tags/reinforcement-learning.md>), [text](<https://devfeed.tech/tags/text.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

PhyCAD trains language models to generate executable CadQuery programs that satisfy geometric and physical constraints, addressing the fact that geometric correctness alone does not ensure physical feasibility. Its dataset links parametric models with geometric specifications, loading conditions, and physical constraints; an automated CAD-CAE verifier combines program execution, geometric checks, and finite element analysis to provide training feedback. To keep unmet requirements from being offset by gains on other criteria, its Hierarchical Balanced Advantage for Group Relative Policy Optimization ranks candidates by verification status, then provides objective-wise peer feedback within each level. Experiments across multiple language models report improved joint geometric and physical constraint satisfaction. The supplied text is an abstract and does not provide quantitative results or implementation details.

### Source excerpt

arXiv:2611.09401v1 Announce Type: new Abstract: Language-driven computer-aided design (CAD) generation enables the creation of editable parametric models from text, yet geometric correctness alone does not ensure physical feasibility. We present PhyCAD, a framework for physics-aware Text-to-CAD generation that trains language models to produce executable CadQuery programs under geometric and physical constraints. To support this setting, we construct a Text-to-CAD dataset that links parametric CAD models with geometric specifications, loading conditions, and physical constraints. We further develop an automated CAD--CAE verifier that combines program execution, geometric checks, and finite element analysis to provide feedback for model training. A key learning challenge is to prioritize joint satisfaction of geometric and physical constraints while retaining informative feedback on partial progress. A flat aggregation of heterogeneous rewards can obscure this priority, allowing improvements in individual criteria to compensate for unmet design requirements. We therefore introduce a Hierarchical Balanced Advantage for Group Relative Policy Optimization, grouping candidates into levels according to their verification status and combining between-level progress with objective-wise peer ranking within each level. This formulation preserves cross-level priority in the training signal while providing fine-grained feedback for satisfying constraints and improving feasible designs. Experiments across multiple language models show that PhyCAD consistently improves joint geometric and physical constraint satisfaction. These results demonstrate the value of verifiable engineering feedback for advancing language-driven CAD generation beyond geometric reconstruction toward physics-aware design.

## TraceCAD: Trace-Guided Repair for Agentic CAD Generation

DevFeed: [TraceCAD: Trace-Guided Repair for Agentic CAD Generation](<https://devfeed.tech/articles/tracecad-trace-guided-repair-for-agentic-cad-generation-118041.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.03062>)

Author: Fengxiao Fan, Jingzhe Ni, Fan Sang, Xiaolong Yin, Yu Liu, Ruofeng Tong, Min Tang, Peng Du

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [CadQuery](<https://devfeed.tech/topics/cadquery.md>), [Software](<https://devfeed.tech/topics/software.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [bounded](<https://devfeed.tech/tags/bounded.md>), [cad](<https://devfeed.tech/tags/cad.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-gr](<https://devfeed.tech/tags/cs-gr.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [edits](<https://devfeed.tech/tags/edits.md>), [execution](<https://devfeed.tech/tags/execution.md>), [failed](<https://devfeed.tech/tags/failed.md>), [generation](<https://devfeed.tech/tags/generation.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [memory](<https://devfeed.tech/tags/memory.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [regression](<https://devfeed.tech/tags/regression.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [repair](<https://devfeed.tech/tags/repair.md>), [results](<https://devfeed.tech/tags/results.md>), [retries](<https://devfeed.tech/tags/retries.md>), [store](<https://devfeed.tech/tags/store.md>)

### AI overview

TraceCAD improves CAD-agent repair by preserving links between requested features, modeling steps, failures, and repair outcomes. It diagnoses likely faulty operations, searches bounded edits in their dependency regions, checks candidates by execution and preservation, and stores successful and failed repairs in reusable skill memory. On DeepCAD-derived benchmarks, it reports competitive IoU, Chamfer, and Hausdorff results. Ablations show that removing persistent state nearly halves recovery score, while removing localized search more than doubles geometric regression and doubles code-agent invocations. A skill store initialized on disjoint training models also reduces retries, token cost, and latency.

### Source excerpt

arXiv:2608.03062v2 Announce Type: replace-cross Abstract: LLM-based CAD agents produce executable parametric programs, but their correction loops may lose evidence about satisfied requirements, faulty operations, and prior repairs. We introduce TraceCAD, a recovery layer that links requested features, modeling steps, failure evidence, and candidate outcomes as persistent state. TraceCAD diagnoses likely faulty operations, searches bounded edits in their dependency regions, validates candidates through execution and preservation checks, and retains successful and failed repair outcomes in reusable skill memory. On DeepCAD-derived benchmarks with 200-model ablations and a 1K-model comparison, TraceCAD achieves competitive geometric quality in terms of IoU, Chamfer distance, and Hausdorff distance. Removing persistent state nearly halves recovery score; removing localized search more than doubles geometric regression and doubles code-agent invocations. Initializing the skill store on disjoint training models further reduces retries, token cost, and latency. These results demonstrate that persistent, localized, and reusable recovery improves final CAD quality and repair reliability.

## Can AI Write CAD? Testing LLM-Generated 3D Models for Manufacturability

DevFeed: [Can AI Write CAD? Testing LLM-Generated 3D Models for Manufacturability](<https://devfeed.tech/articles/can-ai-write-cad-testing-llm-generated-3d-models-for-manufacturability-112508.md>)

Original publisher: [Read original article](<https://hackernoon.com/can-ai-write-cad-testing-llm-generated-3d-models-for-manufacturability?source=rss>)

Author: Melody Cole

Published: 2026-11-02T12:48:11Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [CadQuery](<https://devfeed.tech/topics/cadquery.md>), [3D modeling](<https://devfeed.tech/topics/3d-modeling.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-3d-model-generation](<https://devfeed.tech/tags/ai-3d-model-generation.md>), [ai-for-engineering-design](<https://devfeed.tech/tags/ai-for-engineering-design.md>), [ai-generated-cad](<https://devfeed.tech/tags/ai-generated-cad.md>), [cad](<https://devfeed.tech/tags/cad.md>), [cadquery](<https://devfeed.tech/tags/cadquery.md>), [hackernoon-top-story](<https://devfeed.tech/tags/hackernoon-top-story.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mechanical-engineering](<https://devfeed.tech/tags/mechanical-engineering.md>), [parametric-modeling](<https://devfeed.tech/tags/parametric-modeling.md>), [parts](<https://devfeed.tech/tags/parts.md>), [plan](<https://devfeed.tech/tags/plan.md>), [rules](<https://devfeed.tech/tags/rules.md>), [test-plan](<https://devfeed.tech/tags/test-plan.md>), [testing](<https://devfeed.tech/tags/testing.md>)

### AI overview

The article sets out a reproducible plan to test whether LLM-generated CadQuery scripts produce usable parametric CAD, but reports no experiment results yet. Five parts--an L-bracket, shaft coupling, spur gear, electronics enclosure, and bolt-nut-plate assembly--will be tested from fixed prompts, first with one attempt and then with up to three repair prompts. The rubric checks execution, solid validity, dimensions, parametric updates, process-specific digital manufacturability, STEP/STL exports, and repair effort; manual edits count separately. The author illustrates design intent with a parameterized L-bracket script whose geometry is checked against hand-calculated volume and bounding-box dimensions. DFM checks differ by process: FDM rules cover wall thickness, overhangs, hole allowance, and clearances; CNC checks cover tool access, internal radii, and deep narrow holes. Manufacturability is digital unless physical fabrication is explicitly reported. The planned study is small, limited to CadQuery and selected model versions, and includes subjective engineering review.

### Source excerpt

A student's test plan for checking whether LLMs can write usable parametric CAD: five parts, fixed pass/fail rules, and manufacturability checks.