# PBPO: Prefix-Block Policy Optimization for Diffusion Language Models

Authors: Katherine Tieu, Dongqi Fu, Si Zhang, Hanqing Zeng, Tianxin Wei, Chenglin Wei, Yinglong Xia, Hong Li, Jingrui He.

Trains diffusion language models with policy updates conditioned on completed prefix blocks. Applies importance weights and clipping to individual tokens within each block, avoiding the unstable product of all token ratios.

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

[Original paper](https://arxiv.org/abs/2611.07783) · [PDF](https://arxiv.org/pdf/2611.07783) · [HTML](https://arxiv.org/html/2611.07783v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2611.07783/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2611.07783/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2611.07783/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2611.07783/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 0.15.2; literature checked through 2026-11-03.