VeriVLA: Adaptive Test-Time Verification for Flow-Based VLAs with Latent World Models

Xueli Sun; Yuxiang Lu; Yantong Liu; Xianzhe Fan; Xi Chen; Zhe Liu; Hengshuang Zhao

cs.ROOct 15, 2026

VeriVLA: Adaptive Test-Time Verification for Flow-Based VLAs with Latent World Models

Authors: Xueli Sun, Yuxiang Lu, Yantong Liu, Xianzhe Fan, Xi Chen, Zhe Liu, Hengshuang Zhao

Organizations: The University of Hong Kong

Abstract

Flow-based Vision-Language-Action (VLA) policies are inherently stochastic: different noise seeds can produce action chunks of varying quality from the same observation. At test time, however, the policy typically commits to a single sample without an explicit estimate of its quality. In fine-grained manipulation, executing a suboptimal action can irreversibly disrupt task progress and lead to failure. To exploit policy stochasticity, we introduce a training-free two-axis trigger that uses two initial samples to measure within-chunk temporal variation and cross-sample variance, detecting the critical states. Once triggered, a JEPA-based latent world model ranks candidate action chunks by predicting action-conditioned future latent states and the corresponding changes in task progress. By operating in latent space, the verifier avoids pixel reconstruction and enables efficient and more accurate ranking. Across three real-world tasks, $\textit{i.e.,}$ pen insertion, pipetting, and apple placement), our method raises the average completion score from 50.8% to 65.5%, while adding 326 ms for sampling and verification per triggered decision on a single RTX 4090. Consistent gains are also observed in simulation, where the average success rate rises from 66.4% to 73.6% in the clean setting of RoboTwin 2.0, from 62.8% to 69.6% in its randomized setting, and from 96.9% to 97.6% on LIBERO.

Figures & tables

Figure 1: (a) Policy variance in the LIBERO environment. Repeated sampling reveals higher action variance in contact-rich regions, where task failures are most likely to occur. (b) Values of the proposed trigger. The trigger value aligns with task difficulty and the policy’s internal uncertainty. These observations motivate triggering repeated sampling and verification at critical decision steps.

Figure 2: Conceptual comparison between different paradigms. (a1) Sampling-and-selection with VLM: Directly predict the delta progress with the current observation and the action chunk produced by VLAs. (a2) Sampling-and-selection with generative models: Extract the delta progress after generating the estimated future. (b) Model Predictive Control (MPC) with latent world models: Execute action(s) that minimize the latent distance with the goal image. (c) Latent world model verifier (ours): Estimate the future latent and the delta progress in a unified latent space.

Figure 3: Overall pipeline. (a) Two-Axis Trigger. The VLA policy generates two initial action chunk samples, based on which the two-axis trigger decides whether to activate repeated sampling. (b) Latent World Model Verifier. If triggered, the verifier evaluates $K$ candidate chunks and selects the one with the highest estimated delta progress for execution. The JEPA-based latent world model autoregressively takes states, actions, and observations as input and predicts delta progress in the latent space. (c) Attention Mask. The delta progress key is designed to be invisible from other queries to remove possible task-specific shortcuts for world modeling.

Figure 4: Real-world experimental setup. We conduct the real-world experiments on an AgileX PiperX dual-arm robot, and design three fine-grained tasks, namely, pen insertion, pipetting and apple placement.

Method	Validation Metrics		Completion Score (%) $\uparrow$
Method	Rank Loss $\downarrow$	Huber Loss $\downarrow$	Pen Insertion	Pipetting	Apple Placement	Average
$\pi_{0.5}$ [ 19 ]	–	–	45.0	52.5	55.0	50.8
+ RoboMonkey [ 23 ]	1.19	0.37	49.0	55.5	63.5	56.0
+ GPC-RANK [ 39 ]	1.18	0.30	46.0	54.5	58.0	52.8
+ Ours	1.09	0.25	60.0	63.5	73.0	65.5

Table 1: Comparison of different repeated-sampling-and-selection methods across tasks.

Figure 5: Latency analysis. (a) Additional verification latency per triggered decision for 10 samples under successive optimizations. The three optimization stages cumulatively reduce latency. KV caching provides the largest latency reduction. (b) Trigger rate (left axis) and the resulting average added latency per chunk (right axis) on the three real-world tasks.

Method	Mug	Switch	Seal	Mouse	Scan	Avg.
RoboTwin 2.0 Clean
Hy-VLA	38.0	44.0	74.0	88.0	88.0	66.4
+ RoboMonkey	34.0	48.0	70.0	88.0	86.0	65.2
+ GPC-RANK	42.0	50.0	78.0	88.0	86.0	68.8
+ Ours	48.0	50.0	82.0	96.0	92.0	73.6
RoboTwin 2.0 Clean2Random

Table 2: Results on RoboTwin 2.0 Clean and Clean2Random with always-on verification. Success rates are reported in percent.

Figure 6: Results on RoboTwin 2.0 Clean with Varying Trigger Thresholds. For

\text{trigger}=r

, we adjust a general trigger threshold for all the tasks, so that approximately an

r

fraction of decision steps trigger verification.

Method	Spatial	Object	Goal	10	Avg.
$\pi_{0.5}$	98.8	98.2	98.0	92.4	96.9
+ RoboMonkey	98.6	99.0	97.6	94.0	97.3
+ GPC-RANK	97.6	96.8	97.8	89.0	95.3
+ Ours	98.8	98.8	98.6	94.0	97.6
StarVLA-GR00T	98.0	99.4	96.4	91.0	96.2
+ RoboMonkey	98.2	99.4	96.0	91.6	96.3

Table 3: LIBERO results. Our method boosts the base policy, especially on LIBERO-10, the task suite that has not been saturated.

Method	Rank $\downarrow$	Huber $\downarrow$	Pen $\uparrow$	Pipetting $\uparrow$	Apple $\uparrow$	Avg. $\uparrow$
VeriVLA	1.09	0.25	60.0	63.5	73.0	65.5
w/o WM	1.21	0.26	52.0	55.5	58.0	55.2
w/o pretrain	1.17	0.25	54.0	61.0	63.5	59.5

Table 4: Ablation on world modeling and predictor pretraining. Completion scores (%) are reported overall and per task. The visual encoder remains pretrained in all variants.

Method	Status AUC $\uparrow$	Variance Correlation $\uparrow$	$k$ / add. latency (ms) $\downarrow$
random	0.487	–	–
DINO	0.702	0.630	0 / 0
ACE	0.588	0.716	2 / 14
$T_{\text{temp}}$	0.704	0.789	1 / 0
$T_{\text{cross}}$	0.694	0.877	2 / 14
Ours	0.727	0.887	2 / 14

Table 5: Trigger performance analysis.

k

denotes the number of action samples; latency is additional per decision.

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Method	Trigger	World Modeling	Verification Pipeline	Prediction Target
RoboMonkey	always-on	$\times$	one-stage	action preference
FOREWARN	always-on	✓	two-stage	latent, VLM narration
GPC-RANK	always-on	✓	two-stage	pixel, reward
ADV	always-on	$\times$	one-stage	proximity to discrete action tokens
MG-Select	always-on	$\times$	one-stage	masked-condition divergence
DreamAvoid	vision-based	✓	two-stage	pixel, delta progress

Appendix

Table 6: Comparison of test-time verification methods.

Hyperparameter	Value
Learning rate	$5\times 10^{-4}$
Weight decay	$0.04$
Batch size	32
Optimizer	AdamW
JEPA loss weight	$1$
Rank loss weight	1

Appendix

Table 7: Training hyperparameters and resource configuration. The table specifically shows the real-world adaptation experiments. The actual training epochs and duration can largely depend on the scale of the dataset.

Figure 7: Critical Index and Critical Moments in LIBERO.

Figure 8: Critical Index and Critical Moments in RoboTwin.

Task	Stage	Completion criterion	Score
Pen Insertion	1	Grasp the pen	0.5
Pen Insertion	2	Insert the pen into the yogurt bottle	0.5
Pipetting	1	Move the right hand to the correct position at the right bottle	0.25
	2	Successfully aspirate water with the left hand	0.25
	3	Move the right hand to the correct position at the left bottle	0.25
	4	Successfully dispense water with the left hand	0.25

Appendix

Table 8: Completion score breakdown for the three real-world tasks.

Latency
Component	Latency (ms)
VLA policy	82
Two-Axis Trigger ( $k{=}2$ )	14
Additional sampling ( $K{-}k{=}8$ more candidates)	80
Verifier forward (all $K{=}10$ candidates)	246
Total latency (deactivated)	96

Appendix

Table 9: Latency and GPU memory usage breakdown.

Vision-Language-Action Models

Vision-language-action models turn visual observations and natural-language instructions into actions for robots and other embodied agents.

See all 1,194 papers

CheckVLA: Execution-Time Verification with Action-Conditioned World Model for Long-Horizon Mobile Manipulation
Jul 29, 2026Yushan Liu, Peibo Sun, Xintao Chao +8Long-Horizon Robotic Manipulation World Models for Robotics
Tsinghua University · Shanghai Jiao Tong University · Peking University +2
FATE-VLA:Failue-aware test generation for vision-language-action models
Jun 1, 2026Arusa Kanwal, Pablo Valle, Shaukat Ali +1VLM Evaluation Vision-Language-Action Models
Mondragon University Mondragon, Spain · Simula Research Laboratory Oslo, Norway
TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models
Jun 2, 2026Wenbo Zhang, Jianxiong Li, Shuai Yang +4Test-Time Adaptation Test-Time Adaptation of VLMs
ByteDance Seed · The University of Adelaide · Tsinghua University +3

Jul 29, 2026J/K move · Enter open · S save

CheckVLA: Execution-Time Verification with Action-Conditioned World Model for Long-Horizon Mobile Manipulation

Yushan Liu, Peibo Sun, Xintao Chao, Zhenyang Yang+7

Tsinghua University · Shanghai Jiao Tong University · Peking University+2

Long-Horizon Robotic Manipulation World Models for Robotics Vision-Language-Action Models Runtime Verification

Open paper AskPDF arXiv

Vision-language-action (VLA) policies commonly execute long-horizon mobile manipulation through open-loop action chunks, issuing multiple actions without receiving new high-level visual input. A committed chunk therefore implies how observations should evolve, but accidental deviations can violate this expectation while the remaining actions continue to propagate the error: commit-time policy confidence cannot react to a deviation that occurs after dispatch, and observation-only anomaly scores lack an action-conditioned reference for separating expected effects from unexplained changes. We propose CheckVLA, which verifies execution with a separately trained, frozen action-conditioned world model. A conformally calibrated risk threshold bounds the episode-level probability of an unnecessary first intervention and determines when to intervene, its exceedance controls how strongly the rewritten suffix retains the superseded chunk, latency-aware hard prefixing restricts replacement to actions that remain deployable, and an event-driven keyframe bank preserves evidence of prior progress across repairs. On RoboCasa365, under a common training recipe and a matched invocation budget, CheckVLA attains a 36.1% average success rate against 27.6% for periodic replanning (+8.5 points). At a matched 5% episode-level false-alarm target, action conditioning raises timely recall to 77.9%, against 48.6% for an observation-only control and 37.9% for an action-shuffled control. These simulation results support action-conditioned verification as a way to restore feedback during chunked execution while keeping the repair consistent with inference latency.

Abstract

Vision-Language-Action Models

Explore similar work

CheckVLA: Execution-Time Verification with Action-Conditioned World Model for Long-Horizon Mobile Manipulation

FATE-VLA:Failue-aware test generation for vision-language-action models

TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models