DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models

DACA-GRPO introduces Denoising-Aware Credit Assignment for GRPO-style trainers in Diffusion Language Models. It addresses two weaknesses: lack of temporal credit assignment across denoising steps and bias in mean-field likelihood estimates. DACA-GRPO uses Denoising Progress Scores to extract per-token importance weights from intermediate predictions and Stratified Masking Likelihood to reduce mean-field bias by partitioning token positions. This plug-and-play enhancement achieves consistent improvements across mathematical reasoning, code generation, constraint satisfaction, and JSON schema adherence benchmarks.