Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models

Pengyiang Liu, Junbo Niu, Wenhao Zheng, Xinchen Chen, Canyu Li +3 more
9/28/2026
cs.ROcs.CV

No confident code implementation found for this paper.

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/

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

De-Diffusing WAMs: Action-Sufficient Direct Prediction for Robot Control

87% match2026

LM-X: Explainable Action Modeling with Progress, Event, and Uncertainty Prediction for Generalist Robot Manipulation

86% match2026

Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning

86% match2026

EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents

86% match2026

ΔVLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variation

85% match1 repo132026

PLaCA: Learning Patch-Level Future Latent Change for Action Generation

85% match2026

Cite this paper

@article{liu2026revision,
  title  = {Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models},
  author = {Pengyiang Liu and Junbo Niu and Wenhao Zheng and Xinchen Chen and Canyu Li and Zhongyue Shi and Jiahao Xie and Si Liu},
  year   = {2026},
  eprint = {2609.35439},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2609.35439v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2609.35439.svg)](https://codeofpaper.com/paper/2609.35439)

Discussion