# Breaking Diffusion: Parallel Reasoning with Draft Refinement

Authors: Jaesang Yu, Seoyeon Byun, Yun Wang, Yan Lu, Juho Kim.

Uses one denoiser to revise all tokens in a complete draft in parallel and score the revised draft in context. Repeated refinement keeps the lowest-energy candidate, with experiments on arithmetic, Sudoku and maze solving.

First public: 2026-10-19.
ArXiv initial submission: 2026-10-19.

[Original paper](https://arxiv.org/abs/2610.26542) · [PDF](https://arxiv.org/pdf/2610.26542) · [HTML](https://arxiv.org/html/2610.26542v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.26542/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.26542/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.26542/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.26542/record.json)

## Approaches

- [Alternative generation methods](https://latent-implicit-thinking.github.io/topics/alternative-reasoning-schedules/): Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. Some produce written chains of thought.

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