# Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models

Authors: Yue Yu, Bowen Zuo, David Crandall, Yinglun Zhu, Dongruo Zhou.

Changes how outcome rewards weight decisions at different denoising states during diffusion-model reinforcement learning. Derives the effect for binary rewards and uses matched-scale controls to test whether the schedule improves mathematical accuracy and reasoning-trace diversity.

First public: 2026-09-30.
ArXiv initial submission: 2026-09-30.

[Original paper](https://arxiv.org/abs/2610.00661) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2610.00661/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2610.00661/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2610.00661/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2610.00661/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. These are related approaches: some still produce written chains of thought.

Summary and categories are editorial. Read the original paper to verify claims and limitations. A citation to a paper does not, by itself, establish that a later method builds on it.

Reading-list version 0.9.5; literature checked through 2026-10-18.