# Loopback Transformer: Towards a Unified View of Residual Looped Transformers

Authors: Xuan Ouyang, Zefan Cai, Chenlong Zhang, Cheng Luo, Ke Wan, Junjie Hu.

Treats residual connections as memory across depth. Loopback keeps the original input separate, decays earlier block updates, and learns attention weights over those updates to control their contribution during repeated transformer passes.

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

[Original paper](https://arxiv.org/abs/2611.07226) · [PDF](https://arxiv.org/pdf/2611.07226) · [HTML](https://arxiv.org/html/2611.07226v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2611.07226/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2611.07226/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2611.07226/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2611.07226/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.
- [Analysis and evaluation](https://latent-implicit-thinking.github.io/topics/implicit-reasoning-evaluation/): Measure how well these methods work, investigate what their internal computation does, and identify where they fail. This includes experiments, studies of model internals, and mathematical results.

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