# Extending Reasoning in Typed Decision Models via Adaptive Looping

Authors: David Berghaus, Arber Zela, Behzad Shomali, Markus Frey, Mehdi Ali, Rafet Sifa, Volkan Cevher.

Repeats a shared middle block before scoring answer options, using smaller residual updates when the loop budget grows. Trains one model across several budgets and learns a request-level rule for choosing the amount of computation.

First public: 2026-11-05.
ArXiv initial submission: 2026-11-05.

[Original paper](https://arxiv.org/abs/2611.07736) · [PDF](https://arxiv.org/pdf/2611.07736) · [HTML](https://arxiv.org/html/2611.07736v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2611.07736/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2611.07736/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2611.07736/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2611.07736/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.