# Where KV-Cache Error Lives in Looped Language Models: A Diagnostic Study of Ouro and Huginn

Authors: Dezhen Lu, Runguo Li, Zixiang Ni, Yuchen Tang, Xingquan Kong, Jiaxing Yang, Jiarui Guo, Lingxiang Gao.

Measures how quantizing different loop-specific keys and values changes predictions in Ouro and Huginn. Tests sensitivity-based error estimates and bit allocations, distinguishing typical-sequence behavior from large errors concentrated in a few sequences.

First public: 2026-10-30.
ArXiv initial submission: 2026-10-30.

[Original paper](https://arxiv.org/abs/2610.41825) · [PDF](https://arxiv.org/pdf/2610.41825) · [HTML](https://arxiv.org/html/2610.41825v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.41825/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.41825/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.41825/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.41825/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 0.12.0; literature checked through 2026-11-02.