# World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training

arXiv: https://arxiv.org/abs/2509.24948 · HTML: https://mlsanity.com/paper/2509.24948/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 28 of its 59 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)
- Vision-language-action models / [Reinforcement learning and post-training](https://mlsanity.com/vla/reinforcement-learning-and-post-training/)
- Offline RL and imitation learning from data / [Language-conditioned policies and VLAs](https://mlsanity.com/offlinerl/language-conditioned-policies-and-vlas/)

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023)
- [UniVLA: Learning to Act Anywhere with Task-centric Latent Actions](https://mlsanity.com/paper/2505.06111/) (2025)
- [VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning](https://mlsanity.com/paper/2505.18719/) (2025)
- [FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving](https://mlsanity.com/paper/2505.17685/) (2025)
- [Interactive Post-Training for Vision-Language-Action Models](https://mlsanity.com/paper/2505.17016/) (2025)
- [DiWA: Diffusion Policy Adaptation with World Models](https://mlsanity.com/paper/2508.03645/) (2025)
- [IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model](https://mlsanity.com/paper/2508.06571/) (2025)
- [PWM: Policy Learning with Multi-Task World Models](https://mlsanity.com/paper/2407.02466/) (2024)

## Built on by (most cited first, 30 of 59)

- [DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos](https://mlsanity.com/paper/2602.06949/) (2026)
- [RynnVLA-002: A Unified Vision-Language-Action and World Model](https://mlsanity.com/paper/2511.17502/) (2025)
- [WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL](https://mlsanity.com/paper/2602.13977/) (2026)
- [World Action Models: The Next Frontier in Embodied AI](https://mlsanity.com/paper/2605.12090/) (2026)
- [World Model for Robot Learning: A Comprehensive Survey](https://mlsanity.com/paper/2605.00080/) (2026)
- [From Word to World: Can Large Language Models be Implicit Text-based World Models?](https://mlsanity.com/paper/2512.18832/) (2025)
- [World-VLA-Loop: Closed-Loop Learning of Video World Model and VLA Policy](https://mlsanity.com/paper/2602.06508/) (2026)
- [A Survey on Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2510.24795/) (2025)
- [SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models](https://mlsanity.com/paper/2511.15605/) (2025)
- [AtomVLA: Scalable Post-Training for Robotic Manipulation via Predictive Latent World Models](https://mlsanity.com/paper/2603.08519/) (2026)
- [A Step Toward World Models: A Survey on Robotic Manipulation](https://mlsanity.com/paper/2511.02097/) (2025)
- [Wonder: Video World Model Done Better](https://mlsanity.com/paper/2607.26037/) (2026)
- [World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems](https://mlsanity.com/paper/2604.14732/) (2026)
- [Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test](https://mlsanity.com/paper/2601.04137/) (2026)
- [Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions](https://mlsanity.com/paper/2601.07823/) (2026)
- [Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2602.10503/) (2026)
- [VLANeXt: Recipes for Building Strong VLA Models](https://mlsanity.com/paper/2602.18532/) (2026)
- [ProgressVLA: Progress-Guided Diffusion Policy for Vision-Language Robotic Manipulation](https://mlsanity.com/paper/2603.27670/) (2026)
- [Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training](https://mlsanity.com/paper/2604.21741/) (2026)
- [WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform](https://mlsanity.com/paper/2605.17912/) (2026)
- [How Should World Models Be Evaluated for Embodied Decision-Making? A Decision-Making-Centric Position](https://mlsanity.com/paper/2606.15032/) (2026)
- [World2Act: Latent Action Post-Training from World Model Dynamics](https://mlsanity.com/paper/2603.10422/) (2026)
- [One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy](https://mlsanity.com/paper/2605.07931/) (2026)
- [Learning Transferable Dynamics Priors from Action to World Modeling](https://mlsanity.com/paper/2606.29501/) (2026)
- [Data Pyramid for Embodied Manipulation: A Survey](https://mlsanity.com/paper/2607.24744/) (2026)
- [DreamPlan: Efficient Reinforcement Fine-Tuning of Vision-Language Planners via Video World Models](https://mlsanity.com/paper/2603.16860/) (2026)
- [Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms](https://mlsanity.com/paper/2603.28489/) (2026)
- [HarnessPAI: An Evolving Harness for Physical AI](https://mlsanity.com/paper/2609.29166/) (2026)
- [An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges](https://mlsanity.com/paper/2512.11362/) (2025)
- [Self-Correcting VLA: Online Action Refinement via Sparse World Imagination](https://mlsanity.com/paper/2602.21633/) (2026)

## Abstract (arXiv)

Vision-Language-Action (VLA) models trained via imitation learning suffer from significant performance degradation in data-scarce scenarios due to their reliance on large-scale demonstration datasets. Although reinforcement learning (RL)-based post-training has proven effective in addressing data scarcity, its application to VLA models is hindered by the non-resettable nature of real-world environments. This limitation is particularly critical in high-risk domains such as industrial automation, where interactions often induce state changes that are costly or infeasible to revert. Furthermore, existing VLA approaches lack a reliable mechanism for detecting task completion, leading to redundant actions that reduce overall task success rates. To address these challenges, we propose World-Env, an RL-based post-training framework that replaces physical interaction with a low-cost world model-based virtual simulator. World-Env consists of two key components: (1) a physically-consistent world simulator that generates temporally consistent future visual observations, and (2) a vision-language model (VLM)-guided instant reflector that provides continuous reward signals and predicts action termination. This simulated environment enables VLA models to safely explore and generalize beyond their initial imitation learning distribution. Our method achieves notable performance gains with as few as five expert demonstrations per task. Experiments on complex robotic manipulation tasks demonstrate that World-Env effectively overcomes the data inefficiency, safety constraints, and inefficient execution of conventional VLA models that rely on real-world interaction, offering a practical and scalable solution for post-training in resource-constrained settings. Our code is available at https://github.com/amap-cvlab/world-env.