# iARCS: Iterative Agentic RL for Controllable 3D Scene Generation

arXiv: https://arxiv.org/abs/2608.06161 · HTML: https://mlsanity.com/paper/2608.06161/

## Key facts

- Cited by 1 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 52 of its 71 references that are in the map.
- First posted on arXiv 6 Aug 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 52)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (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)
- [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)
- [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://mlsanity.com/paper/2312.09067/) (2023)
- [Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps](https://mlsanity.com/paper/2501.09732/) (2025)
- [A General Framework for Inference-time Scaling and Steering of Diffusion Models](https://mlsanity.com/paper/2501.06848/) (2025)
- [DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis](https://mlsanity.com/paper/2303.14207/) (2023)
- [Text2Reward: Reward Shaping with Language Models for Reinforcement Learning](https://mlsanity.com/paper/2309.11489/) (2023)
- [PhyScene: Physically Interactable 3D Scene Synthesis for Embodied AI](https://mlsanity.com/paper/2404.09465/) (2024)
- [InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior](https://mlsanity.com/paper/2402.04717/) (2024)
- [GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting](https://mlsanity.com/paper/2402.07207/) (2024)
- [LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models](https://mlsanity.com/paper/2412.02193/) (2024)
- [Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs](https://mlsanity.com/paper/2108.08841/) (2021)
- [Large-scale Reinforcement Learning for Diffusion Models](https://mlsanity.com/paper/2401.12244/) (2024)

## Built on by (most cited first, 1 of 1)

- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)

## Abstract (arXiv)

Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptual realism without reliably satisfying task-critical functional constraints. This mismatch limits the usefulness of synthetic data for downstream training, where accessibility, traversability, and spatial rule compliance are often essential. We present iARCS, an iterative agentic reinforcement learning framework that adapts a pretrained scene generator to naturallanguage task requirements. iARCS uses a two-phase strategy: universal-reward pretraining to improve physical plausibility and layout quality, followed by task-specific finetuning with LLM-generated reward programs that are iteratively refined from training feedback. Experiments show improved constraint fidelity on walkability, reachability, and clearance-focused tasks, effective task-specific constraint optimization, and competitive scene diversity. We further show that data generated by iARCS improves a base generator, supporting its value as a practical synthetic data generation tool rather than only a controllable scene editing method.