VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Mingjian, Zhang, Wenqiao, Yuan, Yuqian, Dai, Yang, Yu, Binhe, Lv, Zheqi, Zheng, Haoyu, Zhu, Jiaqi, Ge, Zhiqi, Wan, Zixuan, Tang, Siliang, Zhuang, Yueting
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911728513581056
author Gao, Mingjian
Zhang, Wenqiao
Yuan, Yuqian
Dai, Yang
Yu, Binhe
Lv, Zheqi
Zheng, Haoyu
Zhu, Jiaqi
Ge, Zhiqi
Wan, Zixuan
Tang, Siliang
Zhuang, Yueting
author_facet Gao, Mingjian
Zhang, Wenqiao
Yuan, Yuqian
Dai, Yang
Yu, Binhe
Lv, Zheqi
Zheng, Haoyu
Zhu, Jiaqi
Ge, Zhiqi
Wan, Zixuan
Tang, Siliang
Zhuang, Yueting
contents Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain-of-thought is a poor fit: irrelevant or weakly textual information can interfere with action prediction, while autoregressive text decoding adds too much latency for real-time closed-loop execution. We present VISUALTHINK-VLA, a visual intermediate-reasoning framework for accurate, low-latency VLA policies. Our bootstrapping philosophy is to guide action with effective visual thinking: VISUALTHINK-VLA bootstraps action prediction through a compact visual-evidence interface that preserves spatial precision while avoiding decoding overhead. Besides, to further improve performance and efficiency, VISUALTHINK-VLA adopts a tailored selective routing mechanism to learn the visual evidence tokens, enabling low-latency inference while preserving high-capacity specialization. We also introduce VisualEvidence-Kit, a supervision-and-audit resource centered on a VisualEvidence-Agent that constructs a 754.7k VLA instructions VisualEvidence-Set for route supervision and counterfactual faithfulness tests. Across multiple benchmarks and real-robot evaluation, VISUALTHINK-VLA achieves the highest success rate on most benchmarks while reducing the multi-second latency of reasoning-augmented baselines to the sub-second regime. For example, on BridgeData V2, it reduces step latency from 8.377,s with ECoT to 0.367,s, achieving a 22.8 times speedup.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30011
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
Gao, Mingjian
Zhang, Wenqiao
Yuan, Yuqian
Dai, Yang
Yu, Binhe
Lv, Zheqi
Zheng, Haoyu
Zhu, Jiaqi
Ge, Zhiqi
Wan, Zixuan
Tang, Siliang
Zhuang, Yueting
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent work has begun to equip vision-language-action (VLA) policies with explicit intermediate reasoning. In embodied control, however, textual chain-of-thought is a poor fit: irrelevant or weakly textual information can interfere with action prediction, while autoregressive text decoding adds too much latency for real-time closed-loop execution. We present VISUALTHINK-VLA, a visual intermediate-reasoning framework for accurate, low-latency VLA policies. Our bootstrapping philosophy is to guide action with effective visual thinking: VISUALTHINK-VLA bootstraps action prediction through a compact visual-evidence interface that preserves spatial precision while avoiding decoding overhead. Besides, to further improve performance and efficiency, VISUALTHINK-VLA adopts a tailored selective routing mechanism to learn the visual evidence tokens, enabling low-latency inference while preserving high-capacity specialization. We also introduce VisualEvidence-Kit, a supervision-and-audit resource centered on a VisualEvidence-Agent that constructs a 754.7k VLA instructions VisualEvidence-Set for route supervision and counterfactual faithfulness tests. Across multiple benchmarks and real-robot evaluation, VISUALTHINK-VLA achieves the highest success rate on most benchmarks while reducing the multi-second latency of reasoning-augmented baselines to the sub-second regime. For example, on BridgeData V2, it reduces step latency from 8.377,s with ECoT to 0.367,s, achieving a 22.8 times speedup.
title VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2605.30011