Future Anchored Verification and Online Recovery for World Action Models

Zhibin Qin; Zhenxiong Tan; Xinchao Wang

cs.ROOct 5, 2026

Future Anchored Verification and Online Recovery for World Action Models

Authors: Zhibin Qin, Zhenxiong Tan, Xinchao Wang

Organizations: National University of Singapore

Abstract

World action models (WAMs) have emerged as a promising paradigm for robotic manipulation. They act by first predicting how a task should be performed and then decoding the actions from that future. However, the remaining actions are invalid once execution drifts from the prediction. Simply replanning from the already out of distribution state rarely restores what the task still requires; existing execution monitors decide when to stop, but not what to restore. We observe that the answer is already in hand: the future the WAM predicted before acting depicts exactly the states it intended to pass through. We introduce FAVOR (Future Anchored Verification and Online Recovery), a lightweight framework that keeps these predicted frames as anchors and uses them for verification and recovery. An Anchor Verifier compares each observation with its anchor, together with the executed actions, to flag deviations that break the task. Anchor-Guided Recovery uses a vision-language model to turn the flagged anchor into a short corrective instruction. Under strengthened instruction guidance, the WAM executes this instruction to return to the intended future. It then resumes the task. FAVOR raises the task success of the base WAM from 97.85% to 98.10% on LIBERO and from 72.60% to 72.98% on LIBERO-Plus without modifying the policy.

Figures & tables

Figure 1: Attention of the frozen WAM under different instructions, with the observation and the random seed fixed. Top: attention of the action tokens. Bottom: attention of the future-video queries over the keys in the video model, under the original prompt, the empty prompt, and their difference. The two conditions produce nearly identical attention maps.

Figure 2: Overview of FAVOR . (a) The frozen WAM predicts future frames and the IDM decodes an action chunk; the predicted frames are retained as anchors. Every $\Delta$ steps, the verifier compares the observation with its anchor: a pass continues execution, and the failure interrupts the remaining actions and triggers recovery. (b) The Anchor Verifier encodes the prediction–observation pair with DINO, fuses it with action and horizon embeddings, and outputs a failure score through a causal GRU; an alarm is raised when the score exceeds $\tau$ . (c) Anchor-Guided Recovery: a VLM reads the alarmed anchor, the current observation, and the task, and issues a corrective instruction.

Figure 3: Effect of the guidance scale on recovery predictions. All branches start from the same trigger state and the corrective instruction “pick up the cup”.

	LIBERO							LIBERO-Plus
	Success (%, $\uparrow$ )					Failure (%, $\downarrow$ )		Success ( $\uparrow$ )
Method	Spatial	Object	Goal	Long	Avg.	Rate	Rel.	Avg.
Fast-WAM-IDM	98.20	98.90	98.30	96.00	97.85	2.15	–	72.60
+ Verifier, direct replanning	98.30	99.20	98.20	96.00	97.92	2.08	$-$ 3.3%	72.60
+ Verifier, correction w/o anchor	98.30	99.30	98.40	96.10	98.02	1.98	$-$ 7.9%	72.53
FAVOR (Anchor-Guided Recovery)	98.30	99.40	98.40	96.30	98.10	1.90	$\mathbf{-}$ 11.6%	72.98

Table 1: Task success (%,

\uparrow

) on LIBERO and LIBERO-Plus, and the LIBERO failure rate (%,

\downarrow

) with its relative change from the base WAM. Bold marks the best entry in each column; the last row gives the gain of FAVOR over the base WAM in percentage points.

Figure 4: Qualitative examples of Anchor-Guided Recovery on LIBERO. In each case, the top row shows the observed execution and the bottom row the WAM’s retained prediction up to the alarm (orange frame); red circles mark where the observation departs from its anchor. Right of the alarm, native continuation under the original instruction fails (top), while the corrective instruction issued by the VLM (green) restores the anchored condition and the task succeeds (bottom). Both branches start from the same simulator state at the alarm.

Figure 5: Distribution of the maximum episode score for successful and failed LIBERO episodes under each detector, on its native scale (higher indicates failure); each point is one episode.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Symbol	Meaning	Value
$H$	Predicted actions per chunk	16
$R$	Executed actions per chunk before replanning	16
$\Delta$	Actions between consecutive anchors	4
$\tau$	Alarm threshold of the fixed operating point	0.5 (LIBERO), 0.9 (LIBERO-Plus)
$B$	Maximum length of the correction window (actions)	64
$\gamma$	Guidance scale during recovery	5

Appendix

Table 3: Default settings of FAVOR in our experiments.

Explore similar work

When to Trust Imagination: Adaptive Action Execution for World Action Models
May 7, 2026Rui Wang, Yue Zhang, Canyang Chen +3Efficient World-Action Model World Models
Southern University of Science and Technology, Shenzhen, China · The University of Hong Kong, Hong Kong, China
HarnessWAM: Bridging Prediction and Deliberation in World Action Models
Aug 10, 2026Zhaopeng Gu, Bingke Zhu, Tianxi Lin +8Efficient World-Action Model Robot State
Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Yinwang Intelligent Technology Co., Ltd., Shenzhen, China +2
Causal-History Test-Time Scaling for Failure Recovery in Autoregressive World-Action Models
Sep 16, 2026Lin Li, Long Chen, Kwunhang +10Efficient World-Action Model Causal
Edwin · The Hong Kong University of Science and Technology (HKUST), ACCESS – AI Chip Center for Emerging Smart Systems, and Zhejiang University. · Zhejiang University. +1

May 7, 2026, cs.ROJ/K move · Enter open · S save

When to Trust Imagination: Adaptive Action Execution for World Action Models

Rui Wang, Yue Zhang, Canyang Chen, Jiehong Lin+2

Southern University of Science and Technology, Shenzhen, China · The University of Hong Kong, Hong Kong, China

Efficient World-Action Model World Models Imagination Long-Horizon Trajectories Causal Attention AI Trustworthiness

Open paper AskPDF arXiv

World Action Models (WAMs) jointly predict future visual observations and actions, but typically execute a fixed number of actions before replanning, regardless of whether the imagined future remains consistent with reality. We formulate adaptive WAM execution as future--reality verification and propose Future Forward Dynamics Causal Attention (FFDC), a lightweight verifier that reasons over predicted actions, predicted visual dynamics, real observations, and instruction-conditioned semantics. FFDC allows continued execution when a plan remains reliable and triggers replanning when its validity deteriorates. We combine verification with Mixture-of-Horizon Training to improve long-horizon trajectory coverage. On RoboTwin, FFDC-WAM achieves the highest average success rate among the evaluated methods in both clean and randomized settings. Under randomization, it improves success by 2.54 percentage points over Base-Motus while reducing WAM planning calls by 69.10% and completion time by 33.88%. Notably, across six real-world tasks on a Unitree G1D robot, FFDC-WAM improves average success by 9.17% over Base-Motus-LC16 while reducing calls by 74.06% and completion time by 51.31%.

Abstract

Explore similar work

When to Trust Imagination: Adaptive Action Execution for World Action Models

HarnessWAM: Bridging Prediction and Deliberation in World Action Models

Causal-History Test-Time Scaling for Failure Recovery in Autoregressive World-Action Models