Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards

arXiv:2510.01544v2 Announce Type: replace Abstract: Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training strategy for improving their performance; however, existing methods rely primarily on outcome-based rewards, which provide no direct supervision over the denoising process and often result in poorly structure