# Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation

arXiv: https://arxiv.org/abs/2505.02836 · HTML: https://mlsanity.com/paper/2505.02836/

## Key facts

- Cited by 67 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 47 of its 55 references that are in the map.
- First posted on arXiv 5 May 2025.

## 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 47)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2004.02857/) (2020)
- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (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)
- [ReconFusion: 3D Reconstruction with Diffusion Priors](https://mlsanity.com/paper/2312.02981/) (2023)
- [3D-FUTURE: 3D Furniture shape with TextURE](https://mlsanity.com/paper/2009.09633/) (2020)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching](https://mlsanity.com/paper/2311.11284/) (2023)
- [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://mlsanity.com/paper/2312.09067/) (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)
- [RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation](https://mlsanity.com/paper/2311.01455/) (2023)
- [WonderWorld: Interactive 3D Scene Generation from a Single Image](https://mlsanity.com/paper/2406.09394/) (2024)
- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [Habitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation](https://mlsanity.com/paper/2306.11290/) (2023)
- [DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis](https://mlsanity.com/paper/2303.14207/) (2023)
- [SceneScape: Text-Driven Consistent Scene Generation](https://mlsanity.com/paper/2302.01133/) (2023)
- [SceneFormer: Indoor Scene Generation with Transformers](https://mlsanity.com/paper/2012.09793/) (2020)
- [WonderJourney: Going from Anywhere to Everywhere](https://mlsanity.com/paper/2312.03884/) (2023)

## Built on by (most cited first, 30 of 67)

- [SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent](https://mlsanity.com/paper/2509.20414/) (2025)
- [SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass](https://mlsanity.com/paper/2508.15769/) (2025)
- [SAGE: Scalable Agentic 3D Scene Generation for Embodied AI](https://mlsanity.com/paper/2602.10116/) (2026)
- [Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning](https://mlsanity.com/paper/2601.11109/) (2026)
- [World-in-World: World Models in a Closed-Loop World](https://mlsanity.com/paper/2510.18135/) (2025)
- [VLM4D: Towards Spatiotemporal Awareness in Vision Language Models](https://mlsanity.com/paper/2508.02095/) (2025)
- [Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks](https://mlsanity.com/paper/2510.25760/) (2025)
- [WorldGen: From Text to Traversable and Interactive 3D Worlds](https://mlsanity.com/paper/2511.16825/) (2025)
- [MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning](https://mlsanity.com/paper/2509.22281/) (2025)
- [3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code](https://mlsanity.com/paper/2606.01057/) (2026)
- [HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Video](https://mlsanity.com/paper/2510.05560/) (2025)
- [Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion](https://mlsanity.com/paper/2511.18734/) (2025)
- [WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis](https://mlsanity.com/paper/2606.01869/) (2026)
- [WorldClaw: Agentic 3D Open-World Generation at Scale](https://mlsanity.com/paper/2608.05248/) (2026)
- [Video Perception Models for 3D Scene Synthesis](https://mlsanity.com/paper/2506.20601/) (2025)
- [CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning](https://mlsanity.com/paper/2601.13304/) (2026)
- [PhyScensis: Physics-Augmented LLM Agents for Complex Physical Scene Arrangement](https://mlsanity.com/paper/2602.14968/) (2026)
- [Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation](https://mlsanity.com/paper/2509.15772/) (2025)
- [DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis](https://mlsanity.com/paper/2510.02178/) (2025)
- [I-Scene: 3D Instance Models are Implicit Generalizable Spatial Learners](https://mlsanity.com/paper/2512.13683/) (2025)
- [SceneReVis: A Self-Reflective Vision-Grounded Framework for 3D Indoor Scene Synthesis via Multi-Turn RL](https://mlsanity.com/paper/2602.09432/) (2026)
- [SceneAssistant: A Visual Feedback Agent for Open-Vocabulary 3D Scene Generation](https://mlsanity.com/paper/2603.12238/) (2026)
- [One Video, One World: Turning Monocular Video into Physical 4D Scenes](https://mlsanity.com/paper/2606.31388/) (2026)
- [ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies](https://mlsanity.com/paper/2506.14315/) (2025)
- [InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity](https://mlsanity.com/paper/2511.18200/) (2025)
- [FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow](https://mlsanity.com/paper/2603.19598/) (2026)
- [SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image](https://mlsanity.com/paper/2606.03994/) (2026)
- [RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills](https://mlsanity.com/paper/2506.14763/) (2025)
- [TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation](https://mlsanity.com/paper/2512.01204/) (2025)
- [Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models](https://mlsanity.com/paper/2604.10578/) (2026)

## Abstract (arXiv)

Synthesizing interactive 3D scenes from text is essential for gaming, virtual reality, and embodied AI. However, existing methods face several challenges. Learning-based approaches depend on small-scale indoor datasets, limiting the scene diversity and layout complexity. While large language models (LLMs) can leverage diverse text-domain knowledge, they struggle with spatial realism, often producing unnatural object placements that fail to respect common sense. Our key insight is that vision perception can bridge this gap by providing realistic spatial guidance that LLMs lack. To this end, we introduce Scenethesis, a training-free agentic framework that integrates LLM-based scene planning with vision-guided layout refinement. Given a text prompt, Scenethesis first employs an LLM to draft a coarse layout. A vision module then refines it by generating an image guidance and extracting scene structure to capture inter-object relations. Next, an optimization module iteratively enforces accurate pose alignment and physical plausibility, preventing artifacts like object penetration and instability. Finally, a judge module verifies spatial coherence. Comprehensive experiments show that Scenethesis generates diverse, realistic, and physically plausible 3D interactive scenes, making it valuable for virtual content creation, simulation environments, and embodied AI research.