# Asymmetric Looped Transformers: Fixed Global Representations for an Iterative Decoder

Authors: Cheng Liang, Tengfei Zhang, Wenjie DU, Jianyu Wu, Changlian Ma, Shuchen Pu, Ya Zhang, Yanfeng Wang, Zhouhan Lin.

Runs a causal encoder once, then repeatedly applies a shared decoder that attends to fixed encoder context and its evolving hidden states. Evaluates this division of work against fully looped and standard language models during pretraining.

First public: 2026-10-20.
ArXiv initial submission: 2026-10-20.

[Original paper](https://arxiv.org/abs/2610.28489) · [PDF](https://arxiv.org/pdf/2610.28489) · [HTML](https://arxiv.org/html/2610.28489v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.28489/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.28489/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.28489/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.28489/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.