parametric cad modeling

In parametric CAD, conventional sketch constraint generation often misaligns with design intent, leading to over-constrained systems or geometric distortions. To address this, we propose “Design Alignment”—a novel paradigm that introduces large language model (LLM) alignment techniques to CAD constraint generation for the first time. Our method establishes a solver-feedback-driven alignment training framework, integrating reasoning-capable LLMs’ semantic understanding with classical geometric constraint modeling to jointly optimize constraint completeness and geometric fidelity. The approach is compatible with existing generative models and achieves a full-constraint satisfaction rate of 93%, substantially outperforming supervised fine-tuning baselines (34%) and non-aligned methods (8.9%). This advancement significantly enhances the editability, robustness, and design-intent consistency of parametric CAD models.

Existing CAD generation methods prioritize visual similarity over geometric precision and suffer from quantization-induced errors in parametric representations, rendering them inadequate for industrial applications demanding exact dimensional accuracy. To address this, this work proposes a Plan-Then-Construct paradigm: first generating a structured design plan with explicit continuous dimensional parameters, then employing a pointer mechanism during the construction phase to directly reference these parameters, thereby enabling high-fidelity modeling. This approach achieves the first end-to-end prediction of continuous parameters, eliminating quantization errors, and ensures dimensional consistency by decoupling parameter inference from geometric construction. We introduce the first large-scale CAD dataset annotated with design plans and propose a three-level geometric evaluation metric—vertices, edges, and faces. Experiments demonstrate that our method significantly outperforms existing approaches across all geometric levels, making it suitable for precision-sensitive engineering tasks.

Existing CAD generation datasets lack the capability to evaluate design intent preservation—specifically, constraint consistency—after parametric edits. This work proposes HistCAD, a CAD-software-agnostic intermediate language that explicitly encodes sketch primitives, geometric and dimensional constraints, feature operations, and 3D boundary references within sequential representations. Leveraging this representation, we construct a dataset of 170,000 executable sequences and establish a new benchmark focused on editability. We introduce three metrics—Edit Reachability (ER), constraint-preserving command sequence ratio (cPCSR), and operation edit similarity (OES)—to distinguish between edit accessibility and constraint preservation. Experiments demonstrate that explicit constraint modeling is crucial for maintaining design intent. HistCAD enables both text-supervised generation and end-to-end CAD synthesis with large language models, validated on industrial-scale complex models, thereby advancing CAD generation from static shape imitation toward reusable, parameterized sequence synthesis.

This work addresses the paradigmatic divide between parametric modeling and boundary representation (B-Rep) in existing AI-driven CAD systems, which hinders high-fidelity design of complex industrial products. To bridge this gap, we propose FutureCAD, a novel framework that explicitly links large language models (LLMs) with B-Rep geometry. FutureCAD leverages an LLM to generate executable CadQuery scripts and integrates a text-query mechanism with a B-Rep grounding transformer to enable precise mapping from natural language to geometric primitives, thereby unifying parametric operations and B-Rep representations. A key innovation is the introduction of a text-driven geometric primitive selection mechanism that effectively reconciles the two modeling paradigms. Evaluated on a newly curated real-world CAD dataset and trained via supervised fine-tuning and reinforcement learning, FutureCAD achieves state-of-the-art performance in high-fidelity CAD generation, significantly improving modeling accuracy and generalization.

Existing CAD systems suffer from a fundamental disconnect between feature-based parametric modeling and B-rep–based direct modeling, hindering cross-paradigm collaborative editing of geometry, topology, and parametric constraints. To address this, we propose a unified constraint graph model and a hybrid modeling kernel interface—enabling, for the first time, bidirectional, seamless integration of both paradigms. Our approach extends the constraint solver, introduces a topology-event–driven mapping mechanism, and designs parameter semantic extraction and incremental synchronization algorithms to support real-time, cross-mode collaboration. Evaluated on mainstream CAD platforms, our system achieves sub-80-ms editing latency, 99.2% constraint fidelity, and efficient handling of complex assemblies. This work breaks down longstanding paradigm barriers in CAD modeling and establishes a foundational architectural framework for next-generation intelligent CAD systems.

Recovering editable, parameterized CAD construction sequences from geometric inputs such as meshes remains a fundamental challenge in design and manufacturing. This work proposes an IoU-driven hybrid optimization framework that, for the first time, formulates the reconstruction problem as structured CAD program optimization. By leveraging geometric feedback, the method iteratively fits and validates a rich set of parametric operations—including fillets and chamfers—within the procedural representation. The approach enables end-to-end image-to-CAD reconstruction across multiple modalities and significantly outperforms existing methods on established benchmarks, achieving superior performance in both volumetric IoU and Chamfer distance metrics. Moreover, it substantially reduces redundancy in the reconstructed programs, enabling efficient and high-fidelity recovery of complex CAD models.

Existing text-to-CAD generation methods struggle to produce mechanical assemblies that are engineering-compliant, physically consistent, and reusable due to their inadequate modeling of multi-part协同 relationships and underlying engineering principles. This work proposes the first axiom-driven assembly generation framework, which translates natural language instructions into structured specifications comprising typed components, geometric ports, executable mating relations, and formal engineering axioms. By leveraging deterministic geometric solvers, the framework generates production-grade CAD assemblies that are verifiable, reusable, and explicitly grounded in engineering principles. The approach enables interpretable and generalizable parametric component synthesis by directly linking engineering intent with geometric realization, significantly outperforming current code-centric methods on the AssemBench benchmark in terms of assembly fidelity, physical validity, and cross-model generalization.

Current large language models (LLMs) can generate syntactically correct CAD scripts, yet they struggle to meet the stringent demands of industrial-grade parametric B-Rep assemblies—particularly in geometric precision, editability, and solver compatibility. This work proposes the first framework that integrates solver feedback into an LLM-driven modeling loop. It employs a hierarchical CAD skill library (L0–L4) to guide an agent in iteratively selecting actions, which are mapped to typed geometric operations, executed in a CAD backend, and refined via solver feedback for planning, repair, and policy learning. By combining action grammar constraints, deterministic parameter parsing, and GRPO-style optimization, the approach achieves high executability in long-horizon, editable assembly modeling. Experiments demonstrate significant success rate improvements on multi-step mechanical, industrial equipment, and mold design tasks, while also highlighting the tension between tool invocation efficiency and long-horizon strategic accuracy.

This work addresses the persistent challenges in fused deposition modeling (FDM) printing—such as poor printability, insufficient mechanical strength, and complex post-processing caused by geometric defects like steep overhangs—by introducing the first end-to-end multi-agent system capable of automatically repairing original CAD models. The proposed framework integrates B-Rep parsing, graph neural network–based semantic recognition, and multimodal large language model reasoning to detect manufacturability issues and generate optimized STEP files along with detailed modification reports. By constructing face adjacency topological graphs, applying GraphSAGE for semantic labeling, leveraging Claude Sonnet for design suggestions, and validating modifications via GPT-4o’s visual reasoning, the system automates the entire pipeline from geometric analysis to natural-language design recommendations. Evaluated on a birdhouse model, it accurately identified overhang regions and effectively proposed corrective strategies such as chamfering, filleting, or part reorientation, substantially overcoming the reliance on manual intervention inherent in traditional design-for-manufacturing approaches.