Newest papers

BrickWright: Agentic Creation of Physically Feasible Brick Builds

Ava Pun, Kevin Dai, Sally Chen, Maxwell Jones, Ruixuan Liu, Kangle Deng, Changliu Liu, Maneesh Agrawala, Deva Ramanan, Jun-Yan Zhu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31651 · cited by 0 works (OpenAlex) · open-access PDF

Spanish

Los agentes de codificación de Frontier Code se están convirtiendo cada vez más capacitados en la modelización 3D. Sin embargo, todavía se enfrentan a desafíos cuando los objetos de construcción están destinados a ser montados en el mundo físico, a menudo creando asambleas inválidas con piezas flotantes, colisionantes o desconectadas. Argumentamos que proporcionar a los agentes herramientas para montar construcciones y verificar su viabilidad física es suficiente para que puedan producir asambleas físicamente válidas que sigan usando solo piezas reales, no tienen piezas de trabajo colisionantes o flotantes y forman una estructura conectada si es posible. BrickWright presenta a BrickWright, un marco para generar construcciones de ladrillo físicamente viables a partir de prompts de texto o de imagen usando agentes físicos pre

Machine translation (Meta M2M100); the English original follows.

Abstract

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: https://avalovelace1.github.io/brickwright/

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Validator, Computer science, Python (programming language), Code (set theory), Software engineering, Human–computer interaction

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange