# Less is More: Recursive Reasoning with Tiny Networks

Authors: Alexia Jolicoeur-Martineau.

Uses one small network to repeatedly update a reasoning state and a proposed answer. Trains these updates with deep supervision and a learned halting score, evaluating the approach on Sudoku, mazes, and ARC-AGI puzzles.

First public: 2025-10-06.
ArXiv initial submission: 2025-10-06.

[Original paper](https://arxiv.org/abs/2510.04871) · [PDF](https://arxiv.org/pdf/2510.04871) · [HTML](https://arxiv.org/html/2510.04871v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2510.04871/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2510.04871/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2510.04871/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2510.04871/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.