Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead and rely on discrete reasoning representations that mismatch continuous perception and control. We propose Latent Reasoning VLA (\textbf{LaRA-VLA}), a unified VLA framework that internalizes multi-modal CoT reasoning into continuous latent representations for embodied action. LaRA-VLA performs unified reasoning and prediction in latent space, eliminating explicit CoT generation at inference time and enabling efficient, action-oriented control. To realize latent embodied reasoning, we introduce a curriculum-based training paradigm that progressively transitions from explicit textual and visual CoT supervision to latent reasoning, and finally adapts latent reasoning dynamics to condition action generation. We construct two structured CoT datasets and evaluate LaRA-VLA on both simulation benchmarks and long-horizon real-robot manipulation tasks. Experimental results show that LaRA-VLA consistently outperforms state-of-the-art VLA methods while reducing inference latency by up to 90\% compared to explicit CoT-based approaches, demonstrating latent reasoning as an effective and efficient paradigm for real-time embodied control. Project Page: \href{https://loveju1y.github.io/Latent-Reasoning-VLA/}{LaRA-VLA Website}.

翻译：视觉-语言-动作（VLA）模型受益于思维链（CoT）推理，但现有方法存在推理开销高、依赖离散推理表征而与连续感知及控制不匹配的问题。我们提出潜在推理VLA（**LaRA-VLA**），一个统一的VLA框架，它将多模态CoT推理内化为面向具身动作的连续潜在表征。LaRA-VLA在潜在空间中执行统一的推理与预测，消除了推理时显式生成CoT的需求，实现了高效、面向动作的控制。为实现潜在的具身推理，我们引入一种基于课程学习的训练范式，逐步从显式的文本与视觉CoT监督过渡到潜在推理，最终将潜在推理动态适配以条件化动作生成。我们构建了两个结构化CoT数据集，并在仿真基准测试和长视野真实机器人操作任务上评估LaRA-VLA。实验结果表明，LaRA-VLA在持续优于最先进VLA方法的同时，与基于显式CoT的方法相比，推理延迟降低了高达90%，证明了潜在推理是实现实时具身控制的一种高效且有效的范式。项目页面：\href{https://loveju1y.github.io/Latent-Reasoning-VLA/}{LaRA-VLA网站}。