ATM is a post-hoc probe-based transfer matrix that diagnoses action consistency in latent world models and serves as a training signal via AITS, enabling fast reliable ranking with claimed 100x speedup over CEM planner evaluation.
Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models
1 Pith paper cite this work. Polarity classification is still indexing.
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.
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ATM: Action-Consistency Transfer Matrix for Diagnosing and Improving Latent World Models
ATM is a post-hoc probe-based transfer matrix that diagnoses action consistency in latent world models and serves as a training signal via AITS, enabling fast reliable ranking with claimed 100x speedup over CEM planner evaluation.