ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models

Cheng Yang; Jianhao Jiao; Lingyi Huang; Jinqi Xiao; Zhexiang Tang; Yu Gong; Yibiao Ying; Yang Sui

cs.CVMar 2, 2026

ATA: Bridging Implicit Reasoning with Attention-Guided and Action-Guided Inference for Vision-Language Action Models

Authors: Cheng Yang, Jianhao Jiao, Lingyi Huang, Jinqi Xiao, Zhexiang Tang, Yu Gong, Yibiao Ying, Yang Sui, +3 more

Organizations: Rutgers University · University College London · Rice University · TCL High-Tech Development Co., Ltd.

Abstract

Vision-Language-Action (VLA) models rely on current observations, including images, language instructions, and robot states, to predict actions and complete tasks. While accurate visual perception is crucial for precise action prediction and execution, recent work has attempted to further improve performance by introducing explicit reasoning during inference. However, such approaches face significant limitations. They often depend on data-intensive resources such as Chain-of-Thought (CoT) style annotations to decompose tasks into step-by-step reasoning, and in many cases require additional visual grounding annotations (e.g., bounding boxes or masks) to highlight relevant image regions. Moreover, they involve time-consuming dataset construction, labeling, and retraining, which ultimately results in longer inference sequences and reduced efficiency. To address these challenges, we propose ATA, a novel training-free framework that introduces implicit reasoning into VLA inference through complementary attention-guided and action-guided strategies. Unlike CoT or explicit visual-grounding methods, ATA formulates reasoning implicitly by integrating attention maps with an action-based region of interest (RoI), thereby adaptively refining visual inputs without requiring extra training or annotations. ATA is a plug-and-play implicit reasoning approach for VLA models, lightweight yet effective. Extensive experiments show that it consistently improves task success and robustness while preserving, and even enhancing, inference efficiency.

Figures & tables

Fig. 1 : Overview of the proposed ATA framework. ( Left ) Given a language instruction and multimodal observations, the VLA model processes tokens through stacked layers to produce an action chunk. Our framework injects implicit reasoning cues via two complementary strategies: ( i ) Attention-guided reasoning extracts attention maps from intermediate layers to focus on task-relevant visual regions; ( ii ) Action-guided reasoning leverages the end-effector pose and camera parameters to construct a directional region of interest (RoI). ( Right ) In the original pipeline (top), an error at an early step may propagate along the horizon (up to $n$ steps), leading to task failure (marked with $\times$ ) and risky behaviors such as knocking over a bottle (highlighted with a red circle ). The proposed pipeline (bottom) applies guidance at selected steps, resulting in a shorter effective horizon ( $m<n$ ), successful task completion (marked with $\checkmark$ ), and more robust execution.

Fig. 2 : Illustration of the action-guided strategy. The end-effector (EEF) pose $(\mathbf{R}^{W}_{\text{EEF}},\mathbf{t}^{W}_{\text{EEF}})$ is obtained in the world coordinate system and transformed into the camera coordinate $(\mathbf{R}^{C}_{\text{EEF}},\mathbf{t}^{C}_{\text{EEF}})$ , allowing projection of the EEF direction onto the image plane. The resulting region of interest (RoI) is represented as a conic sector in the pixel coordinate system. For visualization, we overlay a semi-transparent red mask so that pixels inside the RoI appear in red, while the actual inference mask is computed from Eq. ( 9 ).

Model	Dataset	L	Freq	Time	Step
OpenVLA	Spatial	20	100	periodic	50
	Goal	5	100	periodic	80
	Object	20	100	periodic	60
	10	20	50	periodic	170
$\pi_{0}$ -fast	LIBERO	16/12/12/12	$\infty$	$t=0$	10/7/5/2
HybridVLA	RLBench	5	$\infty$	$t=0$	3

TABLE I : Best configurations of Attention-Guided and Action-Guided strategies. L denotes the attention layer index, Freq denotes the trigger frequency. For

\pi_{0}

-fast and HybridVLA, the attention-guided strategy is applied only once (

\textit{Freq}=\infty

) at the first timestep (

t=0

Models	Method	LIBERO-Spatial	LIBERO-Goal	LIBERO-Object	LIBERO-Long	Avg S.R.	Avg S.I.C $\downarrow$	Avg I.C. $\downarrow$
OpenVLA	Baseline	84.2	75.6	88.6	55.2	75.9	165	235
OpenVLA	API	86.2	78.2	88.6	52	76.3	167	232
OpenVLA	ATTN	87	82	92	57.4	79.6	165	228
OpenVLA	ATA	88.8	82.6	94.6	58.2	81.1	164	225
$\pi_{0}$ -fast	Baseline	96.2	89	98.2	60.2	85.9	30	41
$\pi_{0}$ -fast	API	97.6	88.8	98	60.8	86.3	31	41

TABLE II : Comparison of ATA and Baselines on LIBERO and RLBench. LIBERO includes four datasets, each with 10 tasks and 50 demonstrations per task. The RLBench environment evaluates 8 tasks, each with 100 demonstrations. Avg S.R. denotes the average success rate. Attn denotes the use of only the Attention-Guided strategy, and ATA integrates both Attention-Guided and Action-Guided strategies. Avg S.I.C. indicates the average number of inference calls required for successfully completed tasks, and Avg I.C. represents the overall average number of inference calls across all tasks.

Models	Method	LIBERO-Spatial		LIBERO-Goal		LIBERO-Object		LIBERO-Long		Avg S.R.
OpenVLA	Baseline	84.2		75.6		88.6		55.2		75.9
OpenVLA	Blur	83.4		74.6		84.2		53.2		73.9
OpenVLA	RandomBlur	84.6		77.2		87.2		53.8		75.7
OpenVLA	ATTN*	86.6		80.8		89.2		56.4		78.3
Models	Method	Close box	Close laptop lid	Toilet seat down	Sweep to dustpan	Close fridge	Umbrella out	Wine at rack	Water plants	Avg S.R.
HyBridVLA	Baseline	85	90	90	100	90	40	50	25	71.3

TABLE III : Comparison of Blur, RandomBlur, Attention-Guided, and Baselines on LIBERO and RLBench datasets. Blur represents the Gaussian Blur applied to the first frame, RandomBlur denotes the Gaussian Blur applied randomly to frames after the first frame, and ATTN* indicates the attention-guided strategy applied only on the first frame.

Models	Freq	Spatial	Goal	Object	Long
OpenVLA	0 (Baseline)	84.2	75.6	88.6	55.2
OpenVLA	$\infty$ (ATTN*)	86.6	80.8	89.2	56.4
OpenVLA	20	83.9	78.8	87.8	55.6
OpenVLA	50	86	79.6	89.2	57.4
OpenVLA	100	87	82	92	56.4
OpenVLA	200	86.2	81.2	89.6	55.8

TABLE IV : Comparison of Different Frequencies of Attention-Guided Strategy on LIBERO Dataset Performance. 0 denotes the baseline,

\infty

denotes applying Attention-Guided ( ATTN* ) only on the first timestep (

t=0

), and 20 , 50 , 100 , 200 indicate applying Attention-Guided every 20, 50, 100, and 200 inference steps, respectively.

Panel of Table 7 — TABLE V : Real-world stacking results with and without ATA. Performance is measured on stacking one , two , and three -layer towers of blocks. For the three-tower case, we also tested robustness by adding irrelevant and unseen objects ( Three* ). The bottom-left shows the real-world robotic setup, while the right part illustrates task execution sequences in both simple ( top ) and complex ( bottom ) scenes.

Explore similar work

Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models
Jun 13, 2026Dianqiao Lei, Lianlei ShanEfficient Inference Efficient VLA Model Inference
1Tsinghua University, Beijing, China.
Act, Think or Abstain: Complexity-Aware Adaptive Inference for Vision-Language-Action Models
Mar 5, 2026Riccardo Andrea Izzo, Gianluca Bardaro, Matteo MatteucciVision-Language-Action Models Uncertainty Estimation for VLA Models
All authors are with the Department of Electronics, Information, and Bioengineering, Politecnico di Milano, Milan, Italy.
GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
May 12, 2026Xiaosong Jia, Bowen Yang, Zuhao Ge +17VLM Robustness Robotic Manipulation
Institute of Trustworthy Embodied AI (TEAI), Fudan University · 2Shanghai Key Laboratory of Multimodal Embodied AI · Shanghai Jiao Tong University +1

Jun 13, 2026J/K move · Enter open · S save

Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models

Dianqiao Lei, Lianlei Shan

1Tsinghua University, Beijing, China.

Efficient Inference Efficient VLA Model Inference Efficient VLA Models Latent Visual Reasoning Vision-Language-Action Models VLMs for Robotics+3

Open paper AskPDF arXiv

Existing Vision-Language-Action (VLA) models predominantly rely on explicit Chain-of-Thought (CoT) reasoning to bridge perception and action. While effective, this paradigm suffers from high computational costs and error propagation in multi-step tasks. In this paper, we propose Adaptive Variable Alignment VLA (AVA-VLA), a novel Latent Reasoning VLA framework that models reasoning as a sequence of unobservable latent variables, bypassing the need for explicit text generation. However, latent trajectories are inherently susceptible to noise interference and misalignment with downstream objectives. To address this, we introduce a Reinforcement Learning-based Denoising mechanism that treats latent state generation as a sequential decision process, optimizing reasoning trajectories via task-level rewards. Furthermore, we incorporate an Early-Exit Strategy that adaptively terminates reasoning based on state confidence, enabling a dynamic trade-off between depth and efficiency. Extensive experiments on embodied decision benchmarks demonstrate that AVA-VLA achieves a 6x inference speedup over explicit CoT methods while attaining a 98.3% average success rate on LIBERO, improving both efficiency and long-horizon stability over full-reasoning baselines.

Abstract

Explore similar work

Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models

Act, Think or Abstain: Complexity-Aware Adaptive Inference for Vision-Language-Action Models

GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization