Test-Time Scaling for World Action Models via Zero-Shot Geometric Evaluation

Abstract

Test-time scaling improves foundation-model inference by spending additional computation, but robot control requires deciding whether extra compute is useful before executing an action. World Action Models (WAMs) make this decision natural: each rollout exposes both an action chunk and predicted future observations. We propose \methodgated, a training-free selective test-time scaling framework for WAMs. We first instantiate \method, a fixed-budget Best-of-NN selector that ranks sampled rollouts by cross-view depth reprojection consistency of their predicted futures, computed with a frozen geometry foundation model. \methodgated\ adds a lightweight action--future consistency gate that invokes \method\ only when the initial rollout appears internally inconsistent. Across five benchmark--backbone settings on RoboCasa, LIBERO Long, and RoboTwin~2.0, fixed-budget \method\ improves N=8N{=}8 task success in every setting, e.g., raising the RoboCasa group average from 66.3%66.3\% to 68.4%68.4\% with Cosmos Policy and from 80.8%80.8\% to 82.5%82.5\% with X-WAM. With gating enabled, \methodgated\ recovers on average 74.8%74.8\% of the always-on success gain while triggering additional sampling on only 26.2%26.2\% of decision points. Offline diagnostics show that cross-view reprojection is a strong task-label-free selector, and we identify false low-score selections as a failure mode that helps explain why performance can saturate or degrade as NN increases.