Fast-ThinkAct：通过可言语化潜变量规划实现高效视觉-语言-动作推理
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
把显式思维链压缩成可言语化的潜变量规划，并用偏好引导目标把教师的语言与视觉规划能力蒸馏进学生策略，为视觉研究者提供了一条在保持长程规划与失败恢复能力的同时大幅降低 VLA 推理延迟的可复用思路。
原文依据 Fast-ThinkAct learns to reason efficiently with latent CoTs by distilling from a teacher
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论视觉-语言-动作（VLA）任务需要在复杂视觉场景中进行推理，并在动态环境中执行自适应动作。尽管近期关于推理型 VLA 的研究表明显式思维链（CoT）能够提升泛化能力，但冗长的推理轨迹导致其推理延迟很高。我们提出 Fast-ThinkAct，一个高效的推理框架，通过可言语化的潜变量推理实现紧凑而高性能的规划。Fast-ThinkAct 借助从教师模型蒸馏得到的潜变量思维链进行高效推理，并由一个偏好引导目标驱动，以对齐操作轨迹，从而迁移语言与视觉两方面的规划能力用于具身控制。这使推理增强的策略学习成为可能，有效将紧凑推理与动作执行连接起来。在多种具身操作与推理基准上的大量实验表明，Fast-ThinkAct 取得了强劲性能，相比最优的推理型 VLA 将推理延迟最多降低 89.3%，同时保持有效的长程规划、少样本自适应与失败恢复能力。
英文原文摘要 1143 字符
Vision-Language-Action (VLA) tasks require reasoning over complex visual scenes and executing adaptive actions in dynamic environments. While recent studies on reasoning VLAs show that explicit chain-of-thought (CoT) can improve generalization, they suffer from high inference latency due to lengthy reasoning traces. We propose Fast-ThinkAct, an efficient reasoning framework that achieves compact yet performant planning through verbalizable latent reasoning. Fast-ThinkAct learns to reason efficiently with latent CoTs by distilling from a teacher, driven by a preference-guided objective to align manipulation trajectories that transfers both linguistic and visual planning capabilities for embodied control. This enables reasoning-enhanced policy learning that effectively connects compact reasoning to action execution. Extensive experiments across diverse embodied manipulation and reasoning benchmarks demonstrate that Fast-ThinkAct achieves strong performance with up to 89.3% reduced inference latency over state-of-the-art reasoning VLAs, while maintaining effective long-horizon planning, few-shot adaptation, and failure recovery.