Paper recorded by Signals 4 on 2026-09-11 in cs.LG. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-11 on arXiv · recorded by Signals 4 on 2026-09-14
Category: cs.LG · 机器学习 · first seen 2026-09-14
Diffusion Language Models (DLMs) offer promising parallel generation capabilities but lag behind autoregressive models in complex reasoning and tool-use tasks. While Reinforcement Learning (RL) has recently been applied to enhance DLMs, standard RL approaches suffer from an exploration bottleneck. To address this, we inject reasoning priors from a stronger teacher model to guide RL exploration. In