Looped language models beat parameter-matched dense transformers on all 12 benchmarks using 25x less training data, via a two-stage recipe and minimal dense-to-loop conversion.

Fixed-first training cuts adaptive-depth transformer training compute by 30-45% with negligible quality loss by reserving full-depth updates for a brief final phase.

Looped transformers retain a global workspace, but recurrence reshapes its interfaces: reads and writes follow iteration boundaries, not absolute depth, yet neither model preserves injected content beyond roughly two recurrences.