# What Sets the Serving Speed of Looped Language Models? Measurements and Optimizations Graded by Exactness

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

Measures inference bottlenecks in looped language models and improves cache packing, kernel fusion and prefix reuse. Separates changes that preserve exact outputs from changes to batching, randomness or numerical computation.

First public: 2026-11-03.
ArXiv initial submission: 2026-11-03.

[Original paper](https://arxiv.org/abs/2611.05150) · [PDF](https://arxiv.org/pdf/2611.05150) · [HTML](https://arxiv.org/html/2611.05150v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2611.05150/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2611.05150/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2611.05150/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2611.05150/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 0.15.2; literature checked through 2026-11-03.