embodiedgen-v2-an-agentic-simulation-ready-3d-world-engine-for-embodied-ai

name	embodiedgen-v2-an-agentic-simulation-ready-3d-world-engine-for-embodied-ai
description	We present EmbodiedGen V2, a generative 3D world engine for building executable sim-ready environments for embodied intelligence. Sim-ready 3D asset generation has advanced rapidly, yet assembling suc. Based on arXiv:2607.07459.

EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI

arXiv: 2607.07459 | Authors: Xinjie Wang, Liu Liu, Taojun Ding, Andrew Choi, Chaodong Huang et al. | Utility: 0.87

Overview

We present EmbodiedGen V2, a generative 3D world engine for building executable sim-ready environments for embodied intelligence. Sim-ready 3D asset generation has advanced rapidly, yet assembling such assets into policy-ready task environments remains largely manual, limiting scalable closed-loop learning. EmbodiedGen V2 addresses this gap through a unified sim-ready representation that connects cross-simulator assets, interaction affordances, task-driven worlds, large-scale multi-room scenes, and stateful Vibe Coding into a generative, editable, and reusable simulation pipeline. The generated environments support manipulation, navigation, mobile manipulation, cross-simulator deployment, and embodied policy training. In evaluation, the asset pipeline achieves 96.5% human acceptance and 98.6% collision success, and 83.3% of task-driven worlds are directly usable for downstream simulation without manual modification. Online reinforcement learning with generated environments further improves simulation success from 9.7% to 79.8%, and transfers to real robots with task success increasing from 21.7% to 75.0%. These results establish EmbodiedGen V2 as scalable simulation infrastructure for training, evaluating, and deploying embodied policies.

Key Contributions

1. We present EmbodiedGen V2, a generative 3D world engine for building executable sim-ready environments for embodied intelligence.
2. Sim-ready 3D asset generation has advanced rapidly, yet assembling such assets into policy-ready task environments remains largely manual, limiting scalable closed-loop learning.
3. EmbodiedGen V2 addresses this gap through a unified sim-ready representation that connects cross-simulator assets, interaction affordances, task-driven worlds, large-scale multi-room scenes, and stateful Vibe Coding into a generative, editable, and reusable simulation pipeline.
4. The generated environments support manipulation, navigation, mobile manipulation, cross-simulator deployment, and embodied policy training.

Implementation Notes

• Keywords: agentic, policy-optimization, embodied-ai
• Categories: cs.RO, cs.CV
• Published: 2026-07-08

Activation Criteria

Use this skill when working on tasks involving: agentic, policy-optimization, embodied-ai.