# Causal Latent Workspaces for Looped Transformers

Authors: Ilia Zaznov.

Adds a small, content-addressed memory to a looped transformer, rebuilding causal prefix summaries between shared-layer passes. Tests whether this extra information path improves next-byte prediction under matched parameter and training budgets.

First public: 2026-10-16.
ArXiv initial submission: 2026-10-16.

[Original paper](https://arxiv.org/abs/2610.22796) · [PDF](https://arxiv.org/pdf/2610.22796) · [HTML](https://arxiv.org/html/2610.22796v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.22796/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.22796/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.22796/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.22796/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.