SOURCE-LINKED INTELLIGENCE

World-Coherent Decoding: Self-Verifying Test-Time Planning for World Action Models

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

World Action Models (WAMs) aim to control robots by stochastically generating visual futures and then decoding actions, but empirical observations indicate that the results can strongly depend on which future is selected. We propose World-Coherent-Decoding (WCD), a self-verifying test-time planning framework that treats WAM rollouts as falsifiable future--action hypotheses. At each decision step, WCD samples multiple candidates from a frozen WAM and ranks them using internal generative signals: flow-based video surprisal for visual plausibility and action path effort for action-generation stab

Read original source ↗ Open in workspace

recordType

paper

region

Global