# Not All Loops Cost the Same: Phase-Dependent Depth for Serving Looped Transformers

Authors: Zhixu Du, Yuhan Cheng, Hai "Helen" Li, Yiran Chen.

Uses fewer recurrent steps for prompt tokens while retaining more computation for prompt endpoints and generated tokens. Removes finished positions from later loop calls and adjusts prompt depth as the serving queue grows.

First public: 2026-11-04.
ArXiv initial submission: 2026-11-04.

[Original paper](https://arxiv.org/abs/2611.07211) · [PDF](https://arxiv.org/pdf/2611.07211) · [HTML](https://arxiv.org/html/2611.07211v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2611.07211/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2611.07211/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2611.07211/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2611.07211/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.