Dual-Resolution Recursive Energy for Selective Deliberation in Sequential Decision Making

Fast action selection and slow deliberation are often modeled as separate computational modes. We ask whether they can instead be realized as two evaluation resolutions of a single structured decision model. We introduce a dual-resolution recursive energy model in which contracted macro-energies and explicitly composed AND/OR subtrees evaluate the same action-support structure on a common energy scale. Local expansion controls the extent of explicit deliberation within a decision. Wake–sleep training distills expanded subtree energies into reusable macro-energies and learns estimates of their contraction errors. At inference, these estimates guide which frontier nodes to expand and when the action-energy margin permits stopping. The fully expanded winner is preserved when the predicted errors cover the relevant contraction gaps, or when any remaining undercoverage fits within the action margin. Across BabyAI, MiniHack, and Overcooked-AI, the model reduces explicit recursive expansion by $50.88$–$77.74$% while retaining near-Full macro success, matching Full on Overcooked-AI. It achieves higher macro success than the matched-budget controls in the benchmark-level summaries. On identical held-out decision states, Ours reduces task-averaged median action-selection latency by $26.6$–$57.5$% relative to Full while retaining at least $99.2$% task-averaged action agreement.