Parcae: Scaling Laws For Stable Looped Language Models

Hayden Prairie, Zachary Novack, Taylor Berg-Kirkpatrick, Daniel Y. Fu

Stabilizes looped language models by constraining how earlier states enter the next pass and sampling training depth separately for each sequence. Studies how to divide training compute between data and recurrence, and how additional inference loops reach a performance plateau.

First public: April 14, 2026 · Added to this list: November 3, 2026