Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models

• URL: http://arxiv.org/abs/2605.07514v1
• Date: Fri, 08 May 2026 09:44:43 GMT
• Title: Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models
• Abstract summary: World Action Models (WAMs) enable decision-making through imagined rollouts by predicting future observations and actions.<n>We identify action-state consistency, the alignment between predicted actions and induced state transitions, as a missing reliability axis for WAMs.<n>We introduce a value-free consensus strategy for test-time selection, which ranks candidate rollouts by agreement among predicted futures.
• Score: 28.165928090888986
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: World Action Models (WAMs) enable decision-making through imagined rollouts by predicting future observations and actions. However, the reliability of these imagined futures remains under-examined: is a generated future merely visually plausible, or is it dynamically compatible with the action sequence it claims to model? In this work, we identify action-state consistency, the alignment between predicted actions and induced state transitions, as a missing reliability axis for WAMs. Through a systematic study across representative joint-prediction and inverse-dynamics models, we find that action-state consistency systematically separates successful and failed rollouts across many tasks and follows similar success-failure trends as learned value estimates. These results suggest that consistency captures decision-relevant structure beyond visual realism. We further identify background collapse as an important boundary condition, where low-dynamics failed trajectories can become deceptively consistent because static futures are easier to predict. Building on these findings, we introduce a value-free consensus strategy for test-time selection, which ranks candidate rollouts by agreement among predicted futures. This strategy improves success rates on RoboCasa and RoboTwin 2.0 without additional training or reward modeling. Taken together, our findings establish action-state consistency as both a diagnostic tool for evaluating WAM reliability and a practical signal for value-free planning.

Related papers

• World Models for Embodied Intelligence: From Plausible to Controllable to Actionable [100.13060753774657]
  World models connect perception and decision-making in embodied intelligence by maintaining hidden state, anticipating consequences, comparing interventions, and adapting when execution departs from expectations.<n>This raises a central question: which predictive capabilities improve behavior?<n>We introduce three progressively stronger capability levels: Plausible models preserve task-relevant temporal, geometric, or physical structure; Controllable models additionally predict how interventions alter that structure; and Actionable models translate predictions into measurable gains in planning, action, learning, evaluation, verification, recovery, or data selection.
  arXiv  Detail & Related papers  (2026-09-15T06:22:42Z)
• DA-WAM: Decision-Aligned Future Latents for Driving World Models [6.756366477497099]
  DA-WAM is a framework that unifies predictive representation learning, action-conditioned future modeling, and trajectory scoring under a single decision-making objective.<n>An action-conditioned predictor generates a distinct future latent state per trajectory candidate, which is then evaluated by a future-latent-conditioned factorized scorer.<n>Experiments on NAVSIM-v1 and NAVSIM-v2 demonstrate state-of-the-art performance, while ablations and diagnostic analyses validate the key components.
  arXiv  Detail & Related papers  (2026-08-19T16:33:02Z)
• Overcoming Statistical Bias in Action-Controllable World Models [18.890337378174678]
  Action-conditioned world models aim to predict how visual environments evolve under an agent's actions.<n>Future frames are often highly predictable from visual inertia and recurring motion patterns alone.<n>We introduce CoCo, a Counterfactual Consistency framework to enhance action controllability.
  arXiv  Detail & Related papers  (2026-08-05T10:10:36Z)
• Monitoring the Internal Monologue: Probe Trajectories Reveal Reasoning Dynamics [42.27928681606673]
  Large Reasoning Models (LRMs) introduce new opportunities for safety monitoring through their Chain of Thought (CoT) reasoning.<n>We investigate the hidden representations of LRMs to determine whether future behavior can be predicted from prompt and CoT representations.<n>We find that future model behavior is more distinguishable when examined over the full trajectory than from a single static prediction.
  arXiv  Detail & Related papers  (2026-05-18T15:29:04Z)
• From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation [88.39072412680633]
  We propose MoLA, a control-oriented interface that transforms imagined future videos into executable representations.<n>We evaluate our approach on simulated benchmarks and real-world robot manipulation tasks.
  arXiv  Detail & Related papers  (2026-05-12T14:15:16Z)
• HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models [58.191567345416836]
  World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics.<n>HarmoWAM fully leverages a world model to unify predictive and reactive control, enabling both general transit and precise manipulation.<n>We construct three training-unseen test environments across six real-world robotic tasks, covering variations in background, position, and object semantics.
  arXiv  Detail & Related papers  (2026-05-11T17:59:56Z)
• When to Trust Imagination: Adaptive Action Execution for World Action Models [42.51856318901667]
  World Action Models (WAMs) have recently emerged as a promising paradigm for robotic manipulation by jointly predicting future visual observations and future actions.<n>Current WAMs execute a fixed number of predicted actions after each model inference, leaving the robot blind to whether the imagined future remains consistent with the actual physical rollout.<n>We formulate adaptive WAM execution as a future-reality verification problem: the robot should execute longer when the WAM-predicted future remains reliable, and replan earlier when reality deviates from imagination.
  arXiv  Detail & Related papers  (2026-05-07T13:18:28Z)
• ESIA: An Energy-Based Spatiotemporal Interaction-Aware Framework for Pedestrian Intention Prediction [24.45524909253344]
  Recent advances in autonomous driving have motivated research on pedestrian intention prediction.<n>Existing studies remain constrained by oversimplified multi-agent interaction patterns, opaque reasoning logic, and a lack of global behavioral predictions.<n>We propose Conditional Random Field (CRF)-based paradigm to treat pedestrians and the environment as nodes.
  arXiv  Detail & Related papers  (2026-04-26T14:13:58Z)
• World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry [82.93104394404781]
  General-purpose world models promise scalable policy evaluation, optimization, and planning.<n>We propose World Action Verifier (WAV), a framework that enables world models to identify their own prediction errors and self-improve.
  arXiv  Detail & Related papers  (2026-04-02T12:48:36Z)
• LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning [51.969318585152116]
  LatentPilot exploits future observations during training as a valuable data source to learn action-conditioned visual dynamics.<n>We propose a flywheel-style training mechanism that iteratively collects on-policy trajectories and retrains the model to better match the agent's behavior distribution.<n> Experiments on R2R-CE, RxR-CE, and R2R-PE benchmarks achieve new SOTA results, and real-robot tests across diverse environments demonstrate LatentPilot's superior understanding of environment-action dynamics in scene.
  arXiv  Detail & Related papers  (2026-03-31T02:21:59Z)
• From Passive Metric to Active Signal: The Evolving Role of Uncertainty Quantification in Large Language Models [77.04403907729738]
  This survey charts the evolution of uncertainty from a passive diagnostic metric to an active control signal guiding real-time model behavior.<n>We demonstrate how uncertainty is leveraged as an active control signal across three frontiers.<n>This survey argues that mastering the new trend of uncertainty is essential for building the next generation of scalable, reliable, and trustworthy AI.
  arXiv  Detail & Related papers  (2026-01-22T06:21:31Z)
• VISTA: A Vision and Intent-Aware Social Attention Framework for Multi-Agent Trajectory Prediction [4.4382802228131455]
  We propose VISTA, a goal-conditioned transformer for multi-agent trajectory forecasting.<n>On the high-density MADRAS benchmark, VISTA achieves state-of-the-art accuracy and substantially fewer collisions.<n>These results show that VISTA generates socially compliant, goal-aware, and interpretable trajectories.
  arXiv  Detail & Related papers  (2025-11-13T11:17:01Z)
• UF-RNN: Real-Time Adaptive Motion Generation Using Uncertainty-Driven Foresight Prediction [4.849928323880955]
  Training robots to operate effectively in environments with uncertain states remains a longstanding challenge in robotics.<n>We propose the Uncertainty-driven Foresight Recurrent Neural Network (UF-RNN), a model that combines standard time-series prediction with an active "Foresight" module.<n>UF-RNN exhibits robust adaptation by leveraging self-induced chaotic dynamics in its latent space.<n>These findings suggest that integrating uncertainty-driven foresight into imitation learning pipelines can significantly enhance a robot's ability to handle unpredictable real-world conditions.
  arXiv  Detail & Related papers  (2025-10-11T13:44:20Z)
• Ego-centric Predictive Model Conditioned on Hand Trajectories [52.531681772560724]
  In egocentric scenarios, anticipating both the next action and its visual outcome is essential for understanding human-object interactions.<n>We propose a unified two-stage predictive framework that jointly models action and visual future in egocentric scenarios.<n>Our approach is the first unified model designed to handle both egocentric human activity understanding and robotic manipulation tasks.
  arXiv  Detail & Related papers  (2025-08-27T13:09:55Z)
• Realistic Adversarial Attacks for Robustness Evaluation of Trajectory Prediction Models via Future State Perturbation [1.124958340749622]
  Trajectory prediction is a key element of autonomous vehicle systems.<n>Current approaches tend to focus on perturbing the past positions of surrounding agents.<n>We introduce new performance measures to assess the realism and impact of these adversarial trajectories.
  arXiv  Detail & Related papers  (2025-05-09T15:40:32Z)
• Uncertainty-boosted Robust Video Activity Anticipation [72.14155465769201]
  Video activity anticipation aims to predict what will happen in the future, embracing a broad application prospect ranging from robot vision to autonomous driving. Despite the recent progress, the data uncertainty issue, reflected as the content evolution process and dynamic correlation in event labels, has been somehow ignored. We propose an uncertainty-boosted robust video activity anticipation framework, which generates uncertainty values to indicate the credibility of the anticipation results.
  arXiv  Detail & Related papers  (2024-04-29T12:31:38Z)

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.