Abstract
World-action models use predicted visual futures to condition robot actions, yet execution feedback can invalidate parts of a prediction while leaving its task structure useful. We propose Revisable Temporal Planning (RTP), which maintains the visual future as a persistent action condition and revises it after feedback. Its central mechanism is a learned revision bridge: it resumes an intermediate state saved during visual generation and adapts its continuation to current observations. Visual and action supervision connect this revision to subsequent control. Time-aware history supplies observed evidence, and an adaptive policy selects retention, bridge revision, or fresh replanning from new noise before decoding the next action. On RoboMME and RMBench, RTP achieves task-averaged success rates of 48.6% and 84.8%, respectively. Matched comparisons support learned continuation; estimated checkpoint-source and action-prefix effects are positive but less precisely resolved. These results connect feedback-driven visual-plan revision to closed-loop task performance. Project Page: https://PLACEHOLDER.github.io/RTP/
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Liu, P., Niu, J., Zheng, W., Chen, X., Li, C., Shi, Z., Xie, J., & Liu, S. (2026). Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models. https://omanscience.com/en/articles/revision-not-restart-revisable-visual-plans-for-closed-loop-world-action-models
MLA 9
Liu, Pengyiang, et al. "Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models." https://omanscience.com/en/articles/revision-not-restart-revisable-visual-plans-for-closed-loop-world-action-models.
Chicago (author–date)
Liu, Pengyiang, Junbo Niu, Wenhao Zheng, Xinchen Chen, Canyu Li, Zhongyue Shi, Jiahao Xie, and Si Liu. 2026. "Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models." https://omanscience.com/en/articles/revision-not-restart-revisable-visual-plans-for-closed-loop-world-action-models.
Harvard
Liu, P., Niu, J., Zheng, W., Chen, X., Li, C., Shi, Z., Xie, J. and Liu, S. (2026) 'Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models', Available at: https://omanscience.com/en/articles/revision-not-restart-revisable-visual-plans-for-closed-loop-world-action-models.
Vancouver
Liu P, Niu J, Zheng W, Chen X, Li C, Shi Z, et al. Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models. https://omanscience.com/en/articles/revision-not-restart-revisable-visual-plans-for-closed-loop-world-action-models
IEEE
P. Liu, J. Niu, W. Zheng, X. Chen, C. Li, Z. Shi, J. Xie, and S. Liu, "Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models," https://omanscience.com/en/articles/revision-not-restart-revisable-visual-plans-for-closed-loop-world-action-models.