AI 搭乐高终于不飘了：100% 拼得出来
AI 生成 3D 模型早就行，但让它搭乐高，它给你拼出悬空、穿模、断开的废品——基线模型里最强的也只有 69% 的物理可行率，弱的直接 9%。这篇的解法很朴素：别让 AI 自己瞎摆，给它一套拼搭工具和一个「物理检查员」，拼完先自查再交卷。用这套框架，AI 在 512 个提示词上做到了 100% 的物理有效，而且没牺牲对指令的遵从。它不是你明天能用上的东西，但它是「AI 从画图到造物」这条路上一个实打实的里程碑：当 AI 能保证拼出来的东西真能立住，下一步就是让它帮你设计能实际搭出来的东西。
📄 原文摘要(英文)
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/