# SAGE: Scalable Agentic 3D Scene Generation for Embodied AI

arXiv: https://arxiv.org/abs/2602.10116 · HTML: https://mlsanity.com/paper/2602.10116/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 46 of its 62 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 46)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Evaluating Real-World Robot Manipulation Policies in Simulation](https://mlsanity.com/paper/2405.05941/) (2024)
- [VirtualHome: Simulating Household Activities via Programs](https://mlsanity.com/paper/1806.07011/) (2018)
- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments](https://mlsanity.com/paper/2301.04195/) (2023)
- [ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation](https://mlsanity.com/paper/2007.04954/) (2020)
- [Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models](https://mlsanity.com/paper/2303.11989/) (2023)
- [ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI](https://mlsanity.com/paper/2410.00425/) (2024)
- [RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation](https://mlsanity.com/paper/2311.01455/) (2023)
- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [iGibson 2.0: Object-Centric Simulation for Robot Learning of Everyday Household Tasks](https://mlsanity.com/paper/2108.03272/) (2021)
- [DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis](https://mlsanity.com/paper/2303.14207/) (2023)
- [iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenes](https://mlsanity.com/paper/2012.02924/) (2020)
- [Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation](https://mlsanity.com/paper/2406.11824/) (2024)

## Built on by (most cited first, 30 of 50)

- [SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning](https://mlsanity.com/paper/2605.09423/) (2026)
- [Learning Actionable Manipulation Recovery via Counterfactual Failure Synthesis](https://mlsanity.com/paper/2603.13528/) (2026)
- [WorldClaw: Agentic 3D Open-World Generation at Scale](https://mlsanity.com/paper/2608.05248/) (2026)
- [SceneAssistant: A Visual Feedback Agent for Open-Vocabulary 3D Scene Generation](https://mlsanity.com/paper/2603.12238/) (2026)
- [REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image](https://mlsanity.com/paper/2605.30338/) (2026)
- [One Video, One World: Turning Monocular Video into Physical 4D Scenes](https://mlsanity.com/paper/2606.31388/) (2026)
- [Engine-Native Editable 3D World Reconstruction with Objects and Lighting](https://mlsanity.com/paper/2607.20889/) (2026)
- [Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis](https://mlsanity.com/paper/2605.18451/) (2026)
- [GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction](https://mlsanity.com/paper/2605.23888/) (2026)
- [MUSE: Agentic 3D Scene Authoring via Memory-Grounded Incremental Requirement Satisfaction](https://mlsanity.com/paper/2606.14168/) (2026)
- [Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models](https://mlsanity.com/paper/2608.25518/) (2026)
- [FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute](https://mlsanity.com/paper/2609.08848/) (2026)
- [SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation](https://mlsanity.com/paper/2604.19907/) (2026)
- [ChronoAgentic: A Code-based Multi-Agent World Simulator for Physically Grounded Simulation Construction](https://mlsanity.com/paper/2605.14398/) (2026)
- [WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes](https://mlsanity.com/paper/2605.15843/) (2026)
- [VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?](https://mlsanity.com/paper/2608.15265/) (2026)
- [PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control](https://mlsanity.com/paper/2609.17521/) (2026)
- [3D Generation for Embodied AI and Robotic Simulation: A Survey](https://mlsanity.com/paper/2604.26509/) (2026)
- [EgoKit: Towards Unified Low-Cost Egocentric Data Collection with Heterogeneous Devices](https://mlsanity.com/paper/2605.16797/) (2026)
- [Function2Scene: 3D Indoor Scene Layout from Functional Specifications](https://mlsanity.com/paper/2605.30819/) (2026)
- [iARCS: Iterative Agentic RL for Controllable 3D Scene Generation](https://mlsanity.com/paper/2608.06161/) (2026)
- [NeoWorld-Pro: Programming Interactive Scenes from Monocular Images for Embodied Simulation](https://mlsanity.com/paper/2608.24212/) (2026)
- [GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning](https://mlsanity.com/paper/2609.05927/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis](https://mlsanity.com/paper/2609.26793/) (2026)
- [Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence](https://mlsanity.com/paper/2609.35432/) (2026)
- [CADForge: Agentic Single-View CAD Reconstruction with Explicit Geometry Reasoning](https://mlsanity.com/paper/2610.04262/) (2026)
- [SceneTeract: Probing and Improving Agent-Aware Activity Reasoning in 3D Indoor Scenes](https://mlsanity.com/paper/2603.29798/) (2026)
- [V-CAGE: Vision-Closed-Loop Agentic Generation Engine for Robotic Manipulation](https://mlsanity.com/paper/2604.09036/) (2026)
- [VoxScene: Anchor-Conditioned Voxel Diffusion for Indoor Scene Arrangement](https://mlsanity.com/paper/2605.17102/) (2026)

## Abstract (arXiv)

Real-world data collection for embodied agents remains costly and unsafe, calling for scalable, realistic, and simulator-ready 3D environments. However, existing scene-generation systems often rely on rule-based or task-specific pipelines, yielding artifacts and physically invalid scenes. We present SAGE, an agentic framework that, given a user-specified embodied task (e.g., "pick up a bowl and place it on the table"), understands the intent and automatically generates simulation-ready environments at scale. The agent couples multiple generators for layout and object composition with critics that evaluate semantic plausibility, visual realism, and physical stability. Through iterative reasoning and adaptive tool selection, it self-refines the scenes until meeting user intent and physical validity. The resulting environments are realistic, diverse, and directly deployable in modern simulators for policy training. Policies trained purely on this data exhibit clear scaling trends and generalize to unseen objects and layouts, demonstrating the promise of simulation-driven scaling for embodied AI. Code, demos, and the SAGE-10k dataset can be found on the project page here: https://research.nvidia.com/labs/dir/sage/.