Embodied Chain-of-Thought (CoT) reasoning has significantly enhanced Vision-Language-Action (VLA) models, yet current methods rely on rigid templates to specify reasoning primitives (e.g., objects in the scene, high-level plans, structural affordances). These templates can force policies to process irrelevant information that distracts from critical action-prediction signals. This creates a bottleneck: without successful policies, we cannot verify reasoning quality; without quality reasoning, we cannot build robust policies. We introduce R&B-EnCoRe, which enables models to bootstrap embodied reasoning from internet-scale knowledge through self-supervised refinement. By treating reasoning as a latent variable within importance-weighted variational inference, models can generate and distill a refined reasoning training dataset of embodiment-specific strategies without external rewards, verifiers, or human annotation. We validate R&B-EnCoRe across manipulation (Franka Panda in simulation, WidowX in hardware), legged navigation (bipedal, wheeled, bicycle, quadruped), and autonomous driving embodiments using various VLA architectures with 1B, 4B, 7B, and 30B parameters. Our approach achieves 28% gains in manipulation success, 101% improvement in navigation scores, and 21% reduction in collision-rate metric over models that indiscriminately reason about all available primitives. R&B-EnCoRe enables models to distill reasoning that is predictive of successful control, bypassing manual annotation engineering while grounding internet-scale knowledge in physical execution.

翻译：具身思维链推理显著增强了视觉-语言-动作模型，然而现有方法依赖固定模板来指定推理基元（例如场景中的物体、高层规划、结构可供性）。这些模板可能迫使策略处理无关信息，从而分散对关键动作预测信号的注意力。这造成了一个瓶颈：没有成功的策略，我们就无法验证推理质量；没有高质量的推理，我们就无法构建稳健的策略。我们提出了R&B-EnCoRe，使模型能够通过自监督精炼，从互联网规模的知识中引导具身推理。通过将推理视为重要性加权变分推断中的隐变量，模型能够生成并提炼出一个经过精炼的、包含具体化特定策略的推理训练数据集，而无需外部奖励、验证器或人工标注。我们在操作（仿真中的Franka Panda、硬件中的WidowX）、腿部导航（双足、轮式、自行车、四足）和自动驾驶等具身化场景中，使用具有1B、4B、7B和30B参数的各种VLA架构验证了R&B-EnCoRe。相较于不加区分地推理所有可用基元的模型，我们的方法在操作成功率上提升了28%，在导航得分上提高了101%，并在碰撞率指标上降低了21%。R&B-EnCoRe使模型能够提炼出对成功控制具有预测性的推理，绕过了人工标注工程，同时将互联网规模的知识锚定在物理执行中。