# SceneAssistant: A Visual Feedback Agent for Open-Vocabulary 3D Scene Generation

arXiv: https://arxiv.org/abs/2603.12238 · HTML: https://mlsanity.com/paper/2603.12238/

## Key facts

- Cited by 6 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 42 of its 50 references that are in the map.
- First posted on arXiv 12 Mar 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 42)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics](https://mlsanity.com/paper/2011.09127/) (2020)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [LayoutGPT: Compositional Visual Planning and Generation with Large Language Models](https://mlsanity.com/paper/2305.15393/) (2023)
- [3D-FUTURE: 3D Furniture shape with TextURE](https://mlsanity.com/paper/2009.09633/) (2020)
- [Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer](https://mlsanity.com/paper/2511.22699/) (2025)
- [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://mlsanity.com/paper/2312.09067/) (2023)
- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis](https://mlsanity.com/paper/2303.14207/) (2023)
- [Infinite Photorealistic Worlds using Procedural Generation](https://mlsanity.com/paper/2306.09310/) (2023)
- [Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning](https://mlsanity.com/paper/2401.06805/) (2024)
- [SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code](https://mlsanity.com/paper/2403.01248/) (2024)
- [LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models](https://mlsanity.com/paper/2412.02193/) (2024)
- [3D-GPT: Procedural 3D Modeling with Large Language Models](https://mlsanity.com/paper/2310.12945/) (2023)
- [Understanding and Improving Visual Prompting: A Label-Mapping Perspective](https://mlsanity.com/paper/2211.11635/) (2022)
- [I-Design: Personalized LLM Interior Designer](https://mlsanity.com/paper/2404.02838/) (2024)
- [AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes](https://mlsanity.com/paper/2312.06644/) (2023)
- [DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling](https://mlsanity.com/paper/2404.03575/) (2024)
- [Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation](https://mlsanity.com/paper/2505.02836/) (2025)
- [SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent](https://mlsanity.com/paper/2509.20414/) (2025)
- [SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors](https://mlsanity.com/paper/2403.13438/) (2024)
- [Visual Prompting in Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2409.15310/) (2024)
- [Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text](https://mlsanity.com/paper/2406.17601/) (2024)
- [SAGE: Scalable Agentic 3D Scene Generation for Embodied AI](https://mlsanity.com/paper/2602.10116/) (2026)
- [SceneTeller: Language-to-3D Scene Generation](https://mlsanity.com/paper/2407.20727/) (2024)

## Built on by (most cited first, 6 of 6)

- [VibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End?](https://mlsanity.com/paper/2608.15265/) (2026)
- [Function2Scene: 3D Indoor Scene Layout from Functional Specifications](https://mlsanity.com/paper/2605.30819/) (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)
- [To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation](https://mlsanity.com/paper/2608.05879/) (2026)
- [Unravel: Recovering an Interactive 3D Scene from a Single Image](https://mlsanity.com/paper/2610.16146/) (2026)

## Abstract (arXiv)

Text-to-3D scene generation from natural language is highly desirable for digital content creation. However, existing methods are largely domain-restricted or reliant on predefined spatial relationships, limiting their capacity for unconstrained, open-vocabulary 3D scene synthesis. In this paper, we introduce SceneAssistant, a visual-feedback-driven agent designed for open-vocabulary 3D scene generation. Our framework leverages modern 3D object generation model along with the spatial reasoning and planning capabilities of Vision-Language Models (VLMs). To enable open-vocabulary scene composition, we provide the VLMs with a comprehensive set of atomic operations (e.g., Scale, Rotate, FocusOn). At each interaction step, the VLM receives rendered visual feedback and takes actions accordingly, iteratively refining the scene to achieve more coherent spatial arrangements and better alignment with the input text. Experimental results demonstrate that our method can generate diverse, open-vocabulary, and high-quality 3D scenes. Both qualitative analysis and quantitative human evaluations demonstrate the superiority of our approach over existing methods. Furthermore, our method allows users to instruct the agent to edit existing scenes based on natural language commands. Our code is available at https://github.com/ROUJINN/SceneAssistant