| title | ACID: Action Consistency via Inverse Dynamics for Planning with World Models |
|---|---|
| authors | Gawon Seo, Dongwon Kim, Suha Kwak |
| date | 2026-07-02 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2607.02403 |
| upvotes | 21 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| primer | World models |
| abstract | Decision-time planning with action-conditioned world models has become a popular paradigm for embodied control. However, the standard planning cost judges a candidate solely by how close its predicted terminal state lies to the goal, leaving the realizability of the intermediate transitions unchecked -- a predicted trajectory can look convincing while the environment rollout drifts away from it. In this paper, we propose ACID, a decision-time planning framework that introduces cycle action consistency: the action inferred backward from a predicted transition by an inverse dynamics model should recover the one that was conditioned on. We fold this per-step residual into the planning cost via a scale-invariant adaptive weight. Across four action-conditioned world models and six tasks spanning rigid and deformable manipulation, articulated control, and visual navigation, ACID consistently improves planning and matches the baseline's accuracy with substantially less planning compute. |
cite
@misc{seo2026acid,
title={ACID: Action Consistency via Inverse Dynamics for Planning with World Models},
author={Gawon Seo and Dongwon Kim and Suha Kwak},
year={2026},
eprint={2607.02403},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2607.02403}
}