Diffusion-based Vision-Language-Action (VLA) policies have demonstrated strong capability in modeling expressive and multimodal action distributions. However, their reliance on iterative sampling introduces substantial inference latency, which limits their applicability to reactive closed-loop robot manipulation. To address this limitation, we propose \texttt{ReactVLA}, a lightweight and low-latency VLA framework for real-time robotic manipulation. \texttt{ReactVLA} combines two complementary designs: (1) an improved Mean Flow (iMF) action generator that reduces expensive multi-step diffusion sampling to one-to-few-step action generation, and (2) Attention Residuals (AttnRes), a dynamic depth-wise feature routing mechanism that replaces uniform residual accumulation to better preserve task-relevant multimodal representations. We evaluate \texttt{ReactVLA} on large-scale simulation benchmarks, including LIBERO and RoboIMI, as well as real-world robotic manipulation tasks. Experimental results show that \texttt{ReactVLA} consistently outperforms similarly sized VLA baselines, including SmolVLA and $π_0$. On challenging precision manipulation tasks, \texttt{ReactVLA} achieves up to a 1.65$\times$ improvement in task performance while providing more than a 4$\times$ increase in inference speed compared with leading VLA models. Finally, it reduces real-world policy latency to below 38.6 ms, enabling fast reactive control on physical robot platforms. Please check out our project website at: https://game-loader.github.io/ReactVLA/.

翻译：基于扩散的视觉-语言-动作策略在建模表现力丰富的多模态动作分布方面展现了强大能力。然而，该类策略对迭代采样的依赖导致了显著的推理延迟，这限制了其在反应式闭环机器人操作中的应用。为解决这一局限，我们提出了ReactVLA，一种面向实时机器人操作的轻量级低延迟视觉-语言-动作框架。ReactVLA融合了两项互补设计：（1）改进平均流动作生成器，将代价高昂的多步扩散采样压缩为单步或几步动作生成；（2）注意力残差机制，一种动态深度特征路由机制，通过替代均匀残差累积来更好地保留任务相关的多模态表征。我们在包括LIBERO和RoboIMI在内的大规模仿真基准以及真实世界机器人操作任务上对ReactVLA进行了评估。实验结果表明，ReactVLA在任务性能上始终优于同等规模的视觉-语言-动作基线模型（包括SmolVLA和π₀）。在具有挑战性的精密操作任务中，与领先的视觉-语言-动作模型相比，ReactVLA在任务性能上实现了最高1.65倍的提升，同时推理速度提高了4倍以上。最终，它将真实世界策略延迟降至38.6毫秒以下，从而在物理机器人平台上实现了快速反应式控制。请访问我们的项目网站：https://game-loader.github.io/ReactVLA/。