# ARLoop: Fully-Open Pre-trained Looped Transformers with Attention Residuals

Authors: Yuekun Yao, Yupei Du, Dawei Zhu, Huan Sun.

Combines shared transformer layers with attention over recent residual states across recurrent depths. Evaluates the design in controlled pretraining and releases models trained on open language, math and code data.

First public: 2026-11-03.
ArXiv initial submission: 2026-11-03.

[Original paper](https://arxiv.org/abs/2611.05234) · [PDF](https://arxiv.org/pdf/2611.05234) · [HTML](https://arxiv.org/html/2611.05234v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2611.05234/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2611.05234/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2611.05234/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2611.05234/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.