mlsanityData to 7 Oct 2026

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

arXiv 2607.07459 ↗First posted 8 Jul 2026cs.RO cs.CVcited by 4

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

We present EmbodiedGen V2, a generative 3D world engine for building executable policy-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 facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 45 of its 57 references that are in the map. First posted on arXiv 8 Jul 2026.

Builds on

45 of 57 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Agentic 3D Scene Generation with Spatially Contextualized VLMs26 May

Other references · 44

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  3. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  4. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  5. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  7. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  8. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  9. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 882
  10. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  11. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  12. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
32 more
  1. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  2. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  3. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  4. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  5. 2023LayoutGPT: Compositional Visual Planning and Generation with Large Language Modelscited by 337
  6. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 257
  7. 2025SAM 3D: 3Dfy Anything in Imagescited by 230
  8. 2024ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AIcited by 216
  9. 2021Where2Act: From Pixels to Actions for Articulated 3D Objectscited by 179
  10. 2025Native and Compact Structured Latents for 3D Generationcited by 157
  11. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 129
  12. 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Detailscited by 120
  13. 2024PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AIcited by 116
  14. 20213D AffordanceNet: A Benchmark for Visual Object Affordance Understandingcited by 100
  15. 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assetscited by 85
  16. 2023Gen2Sim: Scaling up Robot Learning in Simulation with Generative Modelscited by 62
  17. 2022Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Searchcited by 61
  18. 2025GigaBrain-0: A World Model-Powered Vision-Language-Action Modelcited by 43
  19. 2025PhysX-3D: Physical-Grounded 3D Asset Generationcited by 40
  20. 2025P3-SAM: Native 3D Part Segmentationcited by 39
  21. 2025EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligencecited by 32
  22. 2025GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Trainingcited by 32
  23. 2025PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Imagecited by 32
  24. 2026HoloBrain-0 Technical Reportcited by 20
  25. 2024Chat-Edit-3D: Interactive 3D Scene Editing via Text Promptscited by 19
  26. 2026SegviGen: Repurposing 3D Generative Model for Part Segmentationcited by 9
  27. 20263D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Imagecited by 9
  28. 2026PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual Worldcited by 8
  29. 2026ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100Kcited by 5
  30. 2026Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Modelscited by 3
  31. 2026Scaling Sim-to-Real VLA Reinforcement Learning with Generative 3D Worldscited by 2
  32. 2026RankQ: Offline-to-Online Reinforcement Learning via Self-Supervised Action Rankingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agentscited by 2
  2. 2026EmbodiedSWE: Coding Agents for Long Horizon Dexterous Roboticscited by 2
  3. 2026WorldAgent: Verification-Guided Agentic Physical World Constructioncited by 0
  4. 2026FACT: Fidelity-Aware Construction of Articulated Twinscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 20263D Generation for Embodied AI and Robotic Simulation: A Survey
  2. 2026SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
  3. 2026EmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in Simulation
  4. 2025A Comprehensive Survey on World Models for Embodied AI
  5. 2019Habitat: A Platform for Embodied AI Research
  6. 2026SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
  7. 2025Generative AI in Embodied Systems: System-Level Analysis of Performance, Efficiency and Scalability
  8. 2025A Survey: Learning Embodied Intelligence from Physical Simulators and World Models