English

$\pi$-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs

Robotics 2026-03-10 v2 Computer Vision and Pattern Recognition

Abstract

Flow-based vision-language-action (VLA) models excel in embodied control but suffer from intractable likelihoods during multi-step sampling, hindering online reinforcement learning. We propose \textbf{\textit{π\boldsymbol{\pi}-StepNFT}} (Step-wise Negative-aware Fine-Tuning), a critic-and-likelihood-free framework that requires only a single forward pass per optimization step and eliminates auxiliary value networks. We identify that wider exploration spaces necessitate finer-grained, step-wise guidance for alignment. Empirically, π\pi-StepNFT unlocks latent potential on LIBERO with competitive few-shot robustness. Moreover, it achieves superior generalization on ManiSkill, outperforming value-based baselines in OOD scenarios by preventing overfitting to multimodal features. This property offers a scalable solution promising for complex real-world applications.

Keywords

Cite

@article{arxiv.2603.02083,
  title  = {$\pi$-StepNFT: Wider Space Needs Finer Steps in Online RL for Flow-based VLAs},
  author = {Siting Wang and Xiaofeng Wang and Zheng Zhu and Minnan Pei and Xinyu Cui and Cheng Deng and Jian Zhao and Guan Huang and Haifeng Zhang and Jun Wang},
  journal= {arXiv preprint arXiv:2603.02083},
  year   = {2026}
}