cs.RONov 17, 2026

DailyBrick: Language-Guided Synthesis of Brick Assembly Instructions

Authors: Hang Zhang, Qijian Tian, Yuan Xie, Xuhong Wang, Xin Tan

Abstract

Generating a LEGO model from a user request is more than a plausible 3D shape generation. LEGO models require physical support per brick, and each brick should be placed unblocked. Current methods address this issue by training an expert large language model. We reduce the problem of generating extremely long context on all brick connections to that of writing a program that builds LEGO models like a human, considering each intermediate step could be executed. We introduce DailyBrick , a multi-stage agentic system that produces a LEGO model together with a brick-by-brick assembly instruction for human building and robot assembly. We design a multi-stage harness with roles to help LLMs generate more effectively. A versioned construction SDK compiles multi-level decisions, from semantic subparts to individual bricks, into canonical operations. An external Meta-Reviewer agent replays and inspects the generated package, verifies the model and its construction process, identifies failures, traces them to the responsible stage, and routes them to bounded repairs or to editable candidates for later skill or tool updates. Extensive experiments demonstrate that DailyBrick generates LEGO models based on simple user requests better than recent agentic systems, and show its utility in downstream applications such as robot manipulations on model assembly from instructions and brick sets (https://SpatialAgent.github.io/DailyBrick/).

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. BrickWright: Agentic Creation of Physically Feasible Brick Builds

    Oct 22, 2026Ava Pun, Kevin Dai, Sally Chen +73D Asset GenerationAI Coding Agents

  2. BrickNet: Graph-Backed Generative Brick Assembly

    Apr 24, 2026Peter Kulits, Cordelia SchmidConstrained Generative Modeling3D Asset Generation

  3. BrickBench: Evaluating Agentic Brick Design

    Oct 8, 2026Peter Kulits, Yiqing Xu, R. Kenny Jones +2AI Agent BenchmarksAI Coding Agents