MUSE is a new benchmark and three-stage evaluation protocol for text-to-CAD generation that assesses functionality, manufacturability, and assemblability of B-Rep assemblies beyond geometric similarity.
Generating CAD code with vision-language models for 3d designs
11 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
11
Pith papers citing it
2
external citations · external index
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 11roles
background 1polarities
background 1representative citing papers
CADBench is a new multimodal benchmark for CAD program generation that combines 18k samples from DeepCAD, Fusion 360, ABC, MCB, and Objaverse across clean/noisy meshes and various renders, used to test 11 models and reveal failure modes.
A closed-loop multi-agent system with AutoGen achieves over 98% accuracy in automated concrete barrier design and shows an 8B model outperforming 631B models.
A hybrid agentic architecture integrates knowledge-based physical verification tools into LLM-driven CAD design loops, producing more complex and functionally valid designs than prior agentic baselines.
CAD generation agents are augmented with FEA feedback plus text blueprint and 21-view image signals, raising Box-IoU on S2O and Fusion360 while showing that base models produce no strict-passing FEA artifacts.
Pointer-CAD unifies B-Rep geometry with command sequences via pointer-based entity selection, allowing LLMs to perform complex CAD edits while cutting topological errors from quantization.
Arko-T is a 4B text-to-CAD model that outperforms seven frontier LLMs on 8 of 12 metrics by aligning training to design-state preservation at one-tenth the cost.
Memory-augmented RL agent with case and skill libraries plus dynamic retrieval improves success rate and geometric consistency for complex CAD model generation.
CMAG combines 3D concept scaffolding, prompt decomposition, taxonomy routing, hybrid retrieval, and agentic VLM verification to assemble topologically consistent avatars from catalog assets given free-form text prompts.
CADDesigner is an LLM agent that generates conceptual CAD models from text and sketches via requirement analysis, the ECIP paradigm, and iterative visual feedback, outperforming baselines in experiments.
TRIZ-guided LLM prompting produces structurally diverse CAD chair variants with 4.0-14.7% mass reduction while preserving integrity in a two-stage pipeline.
citing papers explorer
-
MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation
MUSE is a new benchmark and three-stage evaluation protocol for text-to-CAD generation that assesses functionality, manufacturability, and assemblability of B-Rep assemblies beyond geometric similarity.
-
CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation
CADBench is a new multimodal benchmark for CAD program generation that combines 18k samples from DeepCAD, Fusion 360, ABC, MCB, and Objaverse across clean/noisy meshes and various renders, used to test 11 models and reveal failure modes.
-
A Lightweight Multi-Agent Framework for Automated Concrete Barrier Design
A closed-loop multi-agent system with AutoGen achieves over 98% accuracy in automated concrete barrier design and shows an 8B model outperforming 631B models.
-
Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design
A hybrid agentic architecture integrates knowledge-based physical verification tools into LLM-driven CAD design loops, producing more complex and functionally valid designs than prior agentic baselines.
-
Self-Improving CAD Generation Agents with Finite Element Analysis as Feedback
CAD generation agents are augmented with FEA feedback plus text blueprint and 21-view image signals, raising Box-IoU on S2O and Fusion360 while showing that base models produce no strict-passing FEA artifacts.
-
Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection
Pointer-CAD unifies B-Rep geometry with command sequences via pointer-based entity selection, allowing LLMs to perform complex CAD edits while cutting topological errors from quantization.
-
Arko-T: A Foundation Model for Text-to-Structured 3D Generation
Arko-T is a 4B text-to-CAD model that outperforms seven frontier LLMs on 8 of 12 metrics by aligning training to design-state preservation at one-tenth the cost.
-
Memory-Augmented Reinforcement Learning Agent for CAD Generation
Memory-augmented RL agent with case and skill libraries plus dynamic retrieval improves success rate and geometric consistency for complex CAD model generation.
-
CMAG: Concept-Scaffolded Retrieval for Marketplace Avatar Generation
CMAG combines 3D concept scaffolding, prompt decomposition, taxonomy routing, hybrid retrieval, and agentic VLM verification to assemble topologically consistent avatars from catalog assets given free-form text prompts.
-
CADDesigner: Conceptual CAD Model Generation with a General-Purpose Agent
CADDesigner is an LLM agent that generates conceptual CAD models from text and sketches via requirement analysis, the ECIP paradigm, and iterative visual feedback, outperforming baselines in experiments.
-
Enhancing Creativity in 3D Generative Design via a TRIZ-Inspired Text-to-CAD Framework
TRIZ-guided LLM prompting produces structurally diverse CAD chair variants with 4.0-14.7% mass reduction while preserving integrity in a two-stage pipeline.