{"slug": "brickwright-agentic-creation-of-physically-feasible-brick-builds", "title": "BrickWright: Agentic Creation of Physically Feasible Brick Builds", "summary": "A framework called BrickWright, submitted to arXiv on 22 October 2026, guides pre-trained coding agents to generate physically feasible LEGO brick builds from text or image prompts, reaching 100% physical validity on a sample of 512 prompts versus baselines ranging from 9% (GPT-6 Luna) to 69% (GPT-6 Astra). BrickWright works through BrickLayer, a Python toolkit whose brick assembly API halves inference cost compared with working in raw LDraw and whose validator feeds back on physical feasibility, defined as using only real parts with no colliding or floating pieces and a connected structure where possible. The BrickWright-guided agents also improved prompt adherence for lightweight agents, maintained it for stronger agents, and outperformed specialized models on the text-to-brick task, with code available on the project page.", "body_md": "# Computer Science > Computer Vision and Pattern Recognition\n\n  [Submitted on 22 Oct 2026]\n\n# Title:BrickWright: Agentic Creation of Physically Feasible Brick Builds\n\n[View PDF](http://arxiv.org/pdf/2610.31651v1)\n\n[HTML (experimental)](https://arxiv.org/html/2610.31651v1)\n\nAbstract:Frontier coding agents are becoming increasingly adept at 3D modeling. Yet, they still face challenges when building objects meant to be assembled in the physical world, often creating invalid assemblies with floating, colliding, or disconnected parts. We argue that providing agents with tools for assembling builds and verifying their physical feasibility is sufficient for them to produce physically valid assemblies that still adhere to input prompts. Focusing on the domain of LEGO brick builds, we present BrickWright, a framework for generating physically feasible brick builds from text or image prompts using pre-trained agents, where a build is physically feasible if it uses only real parts, has no colliding or floating parts, and forms a connected structure if possible. BrickWright guides agents to create builds by writing code with BrickLayer, a Python toolkit with two main components: an ergonomic brick assembly API that halves inference cost compared to working in raw LDraw, and a validator that provides feedback on physical feasibility. Whereas baseline agents achieve physical validity rates ranging from only 9% (GPT-6 Luna) to 69% (GPT-6 Astra), BrickWright-guided agents achieve 100% validity on a sample of 512 prompts, while improving prompt adherence for lightweight agents and maintaining it for stronger agents. Additionally, they outperform specialized models on the text-to-brick task. Code is available on our project page: [this https URL](https://avalovelace1.github.io/brickwright/)\n\n### Additional Features\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/brickwright-agentic-creation-of-physically-feasible-brick-builds", "canonical_source": "http://arxiv.org/abs/2610.31651v1", "published_at": "2026-10-23 14:39:06+00:00", "updated_at": "2026-10-23 15:10:09.155356+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "computer-vision", "generative-ai"], "entities": ["BrickWright", "BrickLayer", "arXiv", "GPT-6 Luna", "GPT-6 Astra", "LDraw"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/brickwright-agentic-creation-of-physically-feasible-brick-builds", "markdown": "https://wpnews.pro/news/brickwright-agentic-creation-of-physically-feasible-brick-builds.md", "text": "https://wpnews.pro/news/brickwright-agentic-creation-of-physically-feasible-brick-builds.txt", "jsonld": "https://wpnews.pro/news/brickwright-agentic-creation-of-physically-feasible-brick-builds.jsonld"}}