# Parallelizable Probabilistic Latent Reasoning for Diverse Reasoning Trajectories

Authors: Seokhyun Lee, Seongjun Lee, Changhee Lee.

Learns probability distributions over continuous reasoning steps from written reasoning traces, with parallel teacher-forced training. A mixture of latent strategies lets the model sample different solution paths before producing an answer.

First public: 2026-10-21.
ArXiv initial submission: 2026-10-21.

[Original paper](https://arxiv.org/abs/2610.29385) · [PDF](https://arxiv.org/pdf/2610.29385) · [HTML](https://arxiv.org/html/2610.29385v2) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.29385/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.29385/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.29385/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.29385/record.json)
[Code](https://github.com/nshuhsn/PLRM)

## Approaches

- [Continuous-state reasoning](https://latent-implicit-thinking.github.io/topics/continuous-states/): Use vectors—lists of numbers—to carry intermediate reasoning from one step to the next, instead of selecting a text token at every step. Some methods use the model's hidden states; others combine several candidate token representations.

Reading-list version 0.11.0; literature checked through 2026-10-26.