Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
This addresses efficiency issues for embodied AI systems, though it appears incremental as it builds on existing reasoning methods.
The paper tackles the problem of high inference latency in vision-language-action tasks by proposing Fast-ThinkAct, an efficient reasoning framework that reduces latency by up to 89.3% while maintaining strong performance on embodied manipulation and reasoning benchmarks.
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.