CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models
CanvasAnneal is introduced, a curriculum-guided diffusion RL framework that improves over standard diffu-GRPO on MATH500, Countdown, and Tau2 and substantially accelerates reward improvement on several tasks, while gains are task-dependent.
Blake Olson, Yu-Hang Song, Emmett McQuinn et al.
· 0 citations