AI智能体从照片构建3D场景，却无法判断对错
原标题：AI agents build 3D scenes from photos but have no idea if they got it right
AI 摘要
马里兰大学与AWS的研究者提出LEGO-Anything项目，采用Image-to-Code方法，让编码智能体通过迭代编写和修改Blender代码，从单张照片重建可编辑的3D场景。团队同时发布LEGO-Bench基准，包含208张来自模拟器场景的图像，从有效性、重建精度和外观三方面评分。测试显示六种GPT配置几乎都能生成可用场景，但几何精度差异巨大，最佳模型GPT-6 Astra在室内场景仅53.4%、室外39.6%，且智能体无法可靠判断自身结果是否变好。研究者据此开发免训练的LEGO-Plugin，用具体测量替代自我判断，使较弱智能体提升最高达62.7%。
正文节选
AI agents build 3D scenes from photos but have no idea if they got it right Coding agents can build an editable 3D scene from a single photo by writing and refining code step by step. The benchmark that comes with this work reveals where the process still breaks down: self-assessment and geometric accuracy. A 3D reconstruction from a single photo is most useful when it exists as an executable program you can inspect, edit, and query. That's the premise behind LEGO-Anything, a project from resear