Fast-ThinkAct：透過可言語化的潛在規劃實現高效視覺-語言-行動推理

摘要

視覺-語言-行動（VLA）任務需在複雜視覺場景中進行推理，並於動態環境中執行適應性動作。儘管近期研究表明顯性思維鏈（CoT）能提升推理型VLA的泛化能力，但冗長的推理軌跡導致其推論延遲居高不下。我們提出Fast-ThinkAct框架，透過可言語化的潛在推理實現緊湊而高效的規劃。該框架通過從教師模型提煉知識，以偏好引導的目標驅動學習潛在CoT推理，藉此對齊操作軌跡，同時遷移語言與視覺規劃能力以實現具身控制。這種機制使推理增強的策略學習能有效串聯緊湊推理與動作執行。在多樣化具身操作與推理基準測試中，Fast-ThinkAct以較現有最先進推理VLA降低89.3%推論延遲的優勢達成強勁性能，同時保持有效的長程規劃、少樣本適應及錯誤恢復能力。

English

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.

Fast-ThinkAct：透過可言語化的潛在規劃實現高效視覺-語言-行動推理

Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning

摘要

Support