Paper Detail

WorldClaw: Agentic 3D Open-World Generation at Scale

Chunchao Guo, Jinpeng Li, Yang Li, Zilong Huang

huggingface Score 9.4

Published 2026-08-05 · First seen 2026-08-07

General AI

Abstract

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
soon
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{guo2026worldclaw,
  title = {WorldClaw: Agentic 3D Open-World Generation at Scale},
  author = {Chunchao Guo and Jinpeng Li and Yang Li and Zilong Huang},
  year = {2026},
  abstract = {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 },
  url = {https://huggingface.co/papers/2608.05248},
  keywords = {huggingface daily},
  eprint = {2608.05248},
  archiveprefix = {arXiv},
}

Metadata

{}