arXiv Computer Vision By Ava Pun, Kevin Dai, Sally Chen, Maxwell Jones, Ruixuan Liu, Kangle Deng, Changliu Liu, Maneesh Agrawala, Deva Ramanan, Jun-Yan Zhu

BrickWright: Agentic Creation of Physically Feasible Brick Builds

Read the original on arXiv Computer Vision →

BrickWright is a framework that enables coding agents to create physically feasible LEGO brick builds from text or image prompts. It provides a Python toolkit, BrickLayer, which includes an ergonomic assembly API and a validator that checks for real parts, collisions, floating parts, and connectivity. Using BrickWright, agents achieve 100% physical validity on 512 prompts and outperform baseline agents and specialized models on the text-to-brick task.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

arXiv AI
Oct 9

BrickBench: Evaluating Agentic Brick Design

BrickBench is a new benchmark for evaluating agentic, text‑conditioned LEGO‑set design. In each task, an agent receives a prompt and must produce a physically buildable assembly that meets semantic and design criteria by selecting parts from a discrete library while reasoning about local and global constraints. The benchmark scores designs on validity, alignment, and design across three settings that vary in scale and part availability, and it includes BrickAgent, an environment for coding, inspecting, and validating agent outputs.

By Peter Kulits, Yiqing Xu, R. Kenny Jones, Cordelia Schmid, Jiajun Wu
arXiv Computer Vision
Aug 28

Procedura: Agentic 3D Modeling with Procedural Control

Procedura is a new 3D modeling agent that treats 3D shape as code, using a large language model to generate a procedural assembly from a text prompt. It constructs an assembly graph, writes a parametric program with named parts and typed mates, and verifies each part through compile, mate, and connectivity checks before adding it. A vision critic refines the assembly step‑by‑step, and the resulting program includes per‑part materials and simulator‑validated articulation, producing sharp edges and editable, part‑structured outputs that outperform existing native 3D generators on P3D‑Bench and MechBench‑36.

By Youtian Lin, Yikang Yang, Zhanpeng Hu, Mengqi Zhou, Feihu Zhang, Xun Cao, Jiaheng Liu, Yao Yao