# Enabling Dynamic Computation in Looped LMs

Authors: Aayush Mishra, Arnau Padrés Masdemont, Victor Conchello Vendrell, Jordi Ros Giralt, Arash Behboodi, Fabio Valerio Massoli.

Lets tokens leave a looped language model at different depths by reusing their final key-value cache entries in later loops. Adds an exit-depth training objective and ragged-cache training to make variable-depth computation practical.

First public: 2026-10-06.
ArXiv initial submission: 2026-10-06.

[Original paper](https://arxiv.org/abs/2610.09013) · [PDF](https://arxiv.org/pdf/2610.09013) · [HTML](https://arxiv.org/html/2610.09013v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.09013/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.09013/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.09013/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.09013/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 0.11.0; literature checked through 2026-10-26.