# How to Loop Your Transformer: Loop Scaling, Specialization, and Parallel Inference

Authors: Chanakya Ekbote, Artidoro Pagnoni, Devendra Singh Sachan, Shruti Bhosale, Mike Lewis, Maryam Fazel-Zarandi, Shashank Rajput, Sujan Kumar Gonugondla.

Compares which transformer blocks to repeat, how to give each repetition its own small adapter, and how to run loops in parallel during decoding. Separates the effects of state handoffs and shared attention caches across model sizes and compute budgets.

First public: 2026-10-29.
ArXiv initial submission: 2026-10-29.

[Original paper](https://arxiv.org/abs/2610.40325) · [PDF](https://arxiv.org/pdf/2610.40325) · [HTML](https://arxiv.org/html/2610.40325v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.40325/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.40325/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.40325/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.40325/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 0.12.0; literature checked through 2026-11-02.