Reinforcing VLAs in Task-Agnostic World Models

• URL: http://arxiv.org/abs/2605.12334v2
• Date: Wed, 20 May 2026 07:28:11 GMT
• Title: Reinforcing VLAs in Task-Agnostic World Models
• Abstract summary: Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) have emerged as an effective strategy to adapt to new tasks without costly real-world interactions.<n>We argue that world and reward models should capture transferable physical priors that enable zero-shot inference.<n>We propose RAW-Dream, a new paradigm that completely disentangles world model learning from downstream task dependencies.
• Score: 15.056103368344596
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to adapt to new tasks without costly real-world interactions. However, while using imagined trajectories reduces the sample complexity of policy training, existing methods still heavily rely on task-specific data to fine-tune both the world and reward models, fundamentally limiting their scalability to unseen tasks. To overcome this, we argue that world and reward models should capture transferable physical priors that enable zero-shot inference. We propose RAW-Dream (Reinforcing VLAs in task-Agnostic World Dreams), a new paradigm that completely disentangles world model learning from downstream task dependencies. RAW-Dream utilizes a world model pre-trained on diverse task-free behaviors for predicting future rollouts, and an off-the-shelf Vision-Language Model (VLM) for reward generation. Because both components are task-agnostic, VLAs can be readily finetuned for any new task entirely within this zero-shot imagination. Furthermore, to mitigate world model hallucinations, we introduce a dual-noise verification mechanism to filter out unreliable rollouts. Extensive experiments across simulation and real-world settings demonstrate consistent performance gains, proving that generalized physical priors can effectively substitute for costly task-dependent data, offering a highly scalable roadmap for VLA adaptation.

Related papers

• Unleashing More Actions via Action Compositional Training for VLA Models [23.837636418111035]
  Vision-Language-Action models excel at robotic manipulation, driven by the scale and diversity of demonstration data.<n>We propose ACT-VLA (Action Compositional Training for VLA Models), an offline data augmentation framework.<n>By eliminating additional manual data collection, our method automatically expands the training distribution and mitigates overfitting.
  arXiv  Detail & Related papers  (2026-07-01T02:48:17Z)
• EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models [84.73890225707264]
  We present EXPO-FT, a system for stable, sample-efficient RL finetuning of pretrained VLA policies.<n>Our system achieves perfect task performance (30/30 successes) across all evaluated tasks within an average of 19.1 minutes of online robot data.<n>We release an open-source robustness with the aim of facilitating broader adoption of RL finetuning of VLA models in robotics.
  arXiv  Detail & Related papers  (2026-05-25T06:31:03Z)
• Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models [35.944951371813296]
  Vision-Language-Action (VLA) models show strong generalization for robotic control, but finetuning them with reinforcement learning (RL) is constrained by the high cost and safety risks of real-world interaction.<n>We propose VLA-MBPO, a practical framework to tackle these problems in VLA finetuning.<n>Our approach has three key design choices: (i) adapting unified multimodal models for data-efficient world modeling; (ii) an interleaved view decoding mechanism to enforce multi-view consistency; and (iii) chunk-level branched rollout to mitigate error compounding.
  arXiv  Detail & Related papers  (2026-03-21T02:44:39Z)
• Self-Correcting VLA: Online Action Refinement via Sparse World Imagination [55.982504915794514]
  We propose Self-Correcting VLA (SC-VLA), which achieve self-improvement by intrinsically guiding action refinement through sparse imagination.<n>SC-VLA achieve state-of-the-art performance, yielding the highest task throughput with 16% fewer steps and a 9% higher success rate than the best-performing baselines.
  arXiv  Detail & Related papers  (2026-02-25T06:58:06Z)
• VLAW: Iterative Co-Improvement of Vision-Language-Action Policy and World Model [87.75549463328836]
  The goal of this paper is to improve the performance and reliability of vision-language-action (VLA) models through iterative online interaction.<n>We propose a simple iterative improvement algorithm that uses real-world roll-out data to improve the fidelity of the world model.<n>We achieve a 39.2% absolute success rate improvement over the base policy and 11.6% improvement from training with the generated synthetic rollouts.
  arXiv  Detail & Related papers  (2026-02-12T15:21:47Z)
• DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving [52.63591791507895]
  We propose textbfDriveVLA-W0, a training paradigm that employs world modeling to predict future images.<n>This task generates a dense, self-supervised signal that compels the model to learn the underlying dynamics of the driving environment.<n>Experiments on the NAVSIM v1/v2 benchmark and a 680x larger in-house dataset demonstrate that DriveVLA-W0 significantly outperforms BEV and VLA baselines.
  arXiv  Detail & Related papers  (2025-10-14T17:59:47Z)
• ReCoRe: Regularized Contrastive Representation Learning of World Model [21.29132219042405]
  We present a world model that learns invariant features using contrastive unsupervised learning and an intervention-invariant regularizer. Our method outperforms current state-of-the-art model-based and model-free RL methods and significantly improves on out-of-distribution point navigation tasks evaluated on the iGibson benchmark.
  arXiv  Detail & Related papers  (2023-12-14T15:53:07Z)
• Self-Supervised Reinforcement Learning that Transfers using Random Features [41.00256493388967]
  We propose a self-supervised reinforcement learning method that enables the transfer of behaviors across tasks with different rewards. Our method is self-supervised in that it can be trained on offline datasets without reward labels, but can then be quickly deployed on new tasks.
  arXiv  Detail & Related papers  (2023-05-26T20:37:06Z)
• Continual Visual Reinforcement Learning with A Life-Long World Model [55.05017177980985]
  We present a new continual learning approach for visual dynamics modeling.<n>We first introduce the life-long world model, which learns task-specific latent dynamics.<n>Then, we address the value estimation challenge for previous tasks with the exploratory-conservative behavior learning approach.
  arXiv  Detail & Related papers  (2023-03-12T05:08:03Z)
• Goal-Aware Prediction: Learning to Model What Matters [105.43098326577434]
  One of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model and that of the downstream planner or policy. We propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space. We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning.
  arXiv  Detail & Related papers  (2020-07-14T16:42:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.