A Solver-Aided Hierarchical Language for LLM-Driven CAD Design

Simple item page
dc.contributor.authorJones, Ben T.en_US
dc.contributor.authorZhang, Zihanen_US
dc.contributor.authorHähnlein, Felixen_US
dc.contributor.authorMatusik, Wojciechen_US
dc.contributor.authorAhmad, Maazen_US
dc.contributor.authorKim, Vladimiren_US
dc.contributor.authorSchulz, Adrianaen_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.date.accessioned2025-10-07T05:02:28Z
dc.date.available2025-10-07T05:02:28Z
dc.date.issued2025
dc.description.abstractParametric CAD systems use domain-specific languages (DSLs) to represent geometry as programs, enabling both flexible modeling and structured editing. With the rise of large language models (LLMs), there is growing interest in generating such programs from natural language. This raises a key question: what kind of DSL best supports both CAD generation and editing, whether performed by a human or an AI? In this work, we introduce AIDL, a hierarchical, solver-aided DSL designed to align with the strengths of LLMs while remaining interpretable and editable by humans. AIDL enables high-level reasoning by breaking problems into abstract components and structural relationships, while offloading low-level geometric reasoning to a constraint solver. We evaluate AIDL in a 2D text-to-CAD setting using a zero-shot prompt-based interface and compare it to OpenSCAD, a widely used CAD DSL that appears in LLM training data. AIDL produces results that are visually competitive and significantly easier to edit. Our findings suggest that language design is a powerful complement to model training and prompt engineering for building collaborative AI-human tools in CAD. Code is available at https://github.com/deGravity/aidl.en_US
dc.description.number7
dc.description.sectionheadersSynthetizing 3D shapes
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume44
dc.identifier.doi10.1111/cgf.70250
dc.identifier.issn1467-8659
dc.identifier.pages14 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.70250
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf70250
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Software and its engineering → Domain specific languages; Computing methodologies → Shape modeling; Natural language processing; Symbolic and algebraic algorithms; Applied computing → Computer-aided design; Human-centered computing → Systems and tools for interaction design
dc.subjectSoftware and its engineering → Domain specific languages
dc.subjectComputing methodologies → Shape modeling
dc.subjectNatural language processing
dc.subjectSymbolic and algebraic algorithms
dc.subjectApplied computing → Computer
dc.subjectaided design
dc.subjectHuman centered computing → Systems and tools for interaction design
dc.titleA Solver-Aided Hierarchical Language for LLM-Driven CAD Designen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cgf70250.pdf
Size:
2.48 MB
Format:
Adobe Portable Document Format
Download
Collections
44-Issue 7