{"ID":5676799,"CreatedAt":"2026-07-03T03:29:23.032456456Z","UpdatedAt":"2026-07-07T01:06:03.009715918Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.02403","arxiv_id":"2607.02403","title":"ACID: Action Consistency via Inverse Dynamics for Planning with 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.","short_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 tra...","url_abs":"https://arxiv.org/abs/2607.02403","url_pdf":"https://arxiv.org/pdf/2607.02403v1","authors":"[\"Gawon Seo\",\"Dongwon Kim\",\"Suha Kwak\"]","published":"2026-07-02T16:38:10Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.CV\"]","methods":"[]","has_code":false}