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

TL;DR

Fast-ThinkAct introduces an efficient reasoning framework for vision-language-action tasks that reduces inference latency significantly while maintaining strong planning and adaptation capabilities.

Contribution

It presents a novel latent reasoning approach that distills from a teacher, enabling compact, fast, and effective planning in embodied control tasks.

Findings

Achieves up to 89.3% reduction in inference latency

Maintains effective long-horizon planning and few-shot adaptation

Demonstrates strong performance across diverse benchmarks

Abstract

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.