# Parcae: Scaling Laws For Stable Looped Language Models

Authors: 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: 2026-04-14.
ArXiv initial submission: 2026-04-14.

[Original paper](https://arxiv.org/abs/2604.12946) · [PDF](https://arxiv.org/pdf/2604.12946) · [HTML](https://arxiv.org/html/2604.12946v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2604.12946/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2604.12946/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2604.12946/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2604.12946/record.json)

## Approaches

- [Recurrent reasoning](https://latent-implicit-thinking.github.io/topics/recurrent-reasoning/): Repeat parts of the model or keep intermediate information in memory while working through a problem. Some methods also learn how many passes to run.

Reading-list version 0.15.2; literature checked through 2026-11-03.