一句话生成一个可探索的3D世界
现在让AI生成一个能走进去的3D世界，通常要么是空壳、要么是贴图，没法编辑。WorldClaw把这件事拆成流水线：先让规划智能体把文字描述拆成区域、地形、物体清单，再逐层生成——先铺地形骨架，再往重点区域填细节，最后用渲染智能体检查物体和地面是否贴合。结果是一个能自由探索、而且每个物体都能单独拿出来改的完整世界。它不是你明天就能用的工具，但这是从「生成一张图」到「生成一个世界」的关键一步。
📄 原文摘要(英文)
Generating large-scale, freely explorable 3D worlds from open-ended text remains challenging because a system must jointly maintain global spatial coherence, rich local content, and explicit assets suitable for downstream editing and reuse. We present WorldClaw, a fully agentic, coarse-to-fine framework for open-world 3D scene generation. Planning agents translate a text prompt into a structured specification of regions, terrain, assets, materials, and spatial relations. WorldClaw then builds a globally coherent terrain foundation from semantic layouts, reusable assets, generative or procedural materials, and a region-aware height field. For detail-demanding regions, it generates terrain-conditioned compositions, reconstructs editable textured meshes, and recovers their placement on the terrain; render-based agents further refine terrain, objects, appearance, and contacts. Across diverse open-world prompts, WorldClaw produces large-scale scenes with coherent spatial organization, visually compelling local content, and editable instance-level assets while preserving a consistent global terrain structure.