ACID: Action Consistency via Inverse Dynamics for Planning with World Models

• URL: http://arxiv.org/abs/2607.02403v1
• Date: Thu, 02 Jul 2026 16:38:10 GMT
• Title: ACID: Action Consistency via Inverse Dynamics for Planning with World Models
• Abstract summary: ACID is a decision-time planning framework that introduces cycle action consistency.<n>It consistently improves planning and matches the baseline's accuracy with substantially less planning compute.
• Score: 42.33354357727536
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• AdaJEPA: An Adaptive Latent World Model [42.0759614364807]
  We propose AdaJEPA, an adaptive latent world model that performs test-time adaptation within the closed loop of model predictive control (MPC)<n>After training, AdaJEPA plans and executes the first action chunk, uses the observed next-state transition as a self-supervised adaptation signal, and replans with the updated model.<n>This closed-loop update continuously recalibrates the world model without additional expert demonstrations.
  arXiv  Detail & Related papers  (2026-06-30T17:53:48Z)
• AdaReP:Adaptive Re-Planning under Model Mismatch for Neural World-Model Predictive Control [20.745587519033833]
  We analyze how stale-plan penalties scale with the reuse tolerance, the accumulated mismatch since the last replanning step, and the local dynamics sensitivity.<n>We propose AdaReP, a training-free wrapper that adapts the replanning tolerance online using the current deviation from the cached rollout and a local sensitivity estimate.<n>Across image-space planning, latent-space control, and real-world robotic manipulation, AdaReP substantially reduces planner-side computation while maintaining comparable task performance, including over 80% fewer queries on a 50-trial physical robot study.
  arXiv  Detail & Related papers  (2026-06-22T09:27:50Z)
• LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling [74.94985663101906]
  We present LeapTS, a novel framework that reformulates time series forecasting as a dynamic scheduling process over the prediction horizon.<n>We show that LeapTS improves overall forecasting performance by at least 7.4% while achieving a 2.6$times$ to 5.3$times$ inference speedup over representative Transformer-based models.
  arXiv  Detail & Related papers  (2026-05-11T09:54:02Z)
• Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving [52.04950569530877]
  We present Uni-World VLA, a unified vision-language-action model that tightly interleaves future frame prediction and trajectory planning.<n>Our approach achieves competitive closed-loop planning performance while producing high-fidelity future frame predictions.
  arXiv  Detail & Related papers  (2026-03-28T14:39:51Z)
• CorrectionPlanner: Self-Correction Planner with Reinforcement Learning in Autonomous Driving [55.88697462014118]
  CorrectionPlanner is an autoregressive planner with self-correction.<n>It reduces collision rate by over 20% on Waymax and achieves state-of-the-art planning scores on nuPlan.
  arXiv  Detail & Related papers  (2026-03-16T18:03:21Z)
• Agentic Self-Evolutionary Replanning for Embodied Navigation [37.69855672445479]
  Self-Evolutionary RePlanning (SERP) is a paradigm shift from frozen models towards evolving models by run-time learning.<n>In contrast to existing model evolution approaches that often get stuck at predefined static parameters, we introduce agentic self-evolving action model.<n>SERP achieves higher success rate with lower token expenditure over various benchmarks, validating its superior robustness and efficiency across diverse environments.
  arXiv  Detail & Related papers  (2026-03-03T09:12:29Z)
• Compositional Planning with Jumpy World Models [70.74595987225908]
  We study agents that compose pre-trained policies as temporally extended actions, enabling solutions to complex tasks that no constituent alone can solve.<n>Motivated by the geometric policy composition framework introduced in arXiv:2206.08736, we address these challenges by learning predictive models of multi-step dynamics.
  arXiv  Detail & Related papers  (2026-02-23T09:22:21Z)
• TodoEvolve: Learning to Architect Agent Planning Systems [68.48983335970901]
  TodoEvolve is a meta-planning paradigm that autonomously synthesizes and dynamically revises task-specific planning.<n>PlanFactory provides a common interface for heterogeneous planning patterns.<n>TodoEvolve consistently surpasses carefully engineered planning modules while maintaining economical API costs and runtime overhead.
  arXiv  Detail & Related papers  (2026-02-08T06:37:01Z)
• Adaptive Planning with Generative Models under Uncertainty [20.922248169620783]
  Planning with generative models has emerged as an effective decision-making paradigm across a wide range of domains. While continuous replanning at each timestep might seem intuitive because it allows decisions to be made based on the most recent environmental observations, it results in substantial computational challenges. Our work addresses this challenge by introducing a simple adaptive planning policy that leverages the generative model's ability to predict long-horizon state trajectories.
  arXiv  Detail & Related papers  (2024-08-02T18:07:53Z)
• Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty [56.30846158280031]
  Task planning for embodied AI has been one of the most challenging problems. We propose a task-agnostic method named 'planning as in-painting' The proposed framework achieves promising performances in various embodied AI tasks.
  arXiv  Detail & Related papers  (2023-12-02T10:07:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.