{"slug": "can-it-actually-work-synthesizing-functional-cad-mechanisms", "title": "Can It Actually Work? Synthesizing Functional CAD Mechanisms", "summary": "A paper submitted to arXiv on 19 October 2026 proposes FunCAD-Harness, a framework that translates abstract functional requirements into candidate-specific physical tests and uses simulation feedback to guide LLM agents revising CAD mechanisms. The authors also introduce FunCADBench, a benchmark spanning 46 mechanism families with interdependent and multi-step operations, and report that experiments across frontier LLM agents show FunCAD-Harness exposes subtle mechanical failures invisible to visual inspection and substantially improves functional success rates over standard simulation-augmented baselines. The work targets a known gap: LLM agents can generate visually plausible CAD assemblies that fail to fulfill their intended physical functions.", "body_md": "# Computer Science > Computer Vision and Pattern Recognition\n\n  [Submitted on 19 Oct 2026]\n\n# Title:Can It Actually Work? Synthesizing Functional CAD Mechanisms\n\n[View PDF](http://arxiv.org/pdf/2610.26861v1)\n\n[HTML (experimental)](https://arxiv.org/html/2610.26861v1)\n\nAbstract:While LLM agents can generate visually plausible CAD assemblies, these designs often fail to fulfill their intended physical functions. We study functional CAD design, a setting where agents interpret underspecified requests to construct and iteratively revise mechanisms that satisfy functional requirements in physical simulation. Verifying these requirements is nontrivial: different candidate mechanisms may realize the same function through entirely different components, controls, and operating sequences. To bridge this gap, we propose FunCAD-Harness, a framework that translates abstract requirements into candidate-specific physical tests and uses simulation feedback to guide design revisions. To systematically evaluate this capability, we introduce FunCADBench, a benchmark spanning 46 mechanism families with interdependent and multi-step operations. Experiments across frontier LLM agents show that FunCAD-Harness exposes subtle mechanical failures invisible to visual inspection, substantially improving functional success rates over standard simulation-augmented baselines. Ultimately, our work marks a step toward CAD agents capable of translating human intent into working mechanisms.\n    \n\n### Additional Features\n\n### Current browse context:\n\ncs.CV\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/can-it-actually-work-synthesizing-functional-cad-mechanisms", "canonical_source": "http://arxiv.org/abs/2610.26861v1", "published_at": "2026-10-20 14:28:11+00:00", "updated_at": "2026-10-20 14:49:29.903365+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "large-language-models", "computer-vision"], "entities": ["arXiv", "FunCAD-Harness", "FunCADBench"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/can-it-actually-work-synthesizing-functional-cad-mechanisms", "markdown": "https://wpnews.pro/news/can-it-actually-work-synthesizing-functional-cad-mechanisms.md", "text": "https://wpnews.pro/news/can-it-actually-work-synthesizing-functional-cad-mechanisms.txt", "jsonld": "https://wpnews.pro/news/can-it-actually-work-synthesizing-functional-cad-mechanisms.jsonld"}}