Planner Aware Path Learning in Diffusion Language Models Training

ArXi:2509.23405v3 Announce Type: replace Diffusion language models have emerged as a powerful alternative to autoregressive models, enabling fast inference through flexible and parallel generation paths. This flexibility of sampling is unlocked by new engineered sampling strategies, or planners, that select favorable generation paths by iteratively planning - versus uniformly at random - where to denoise along the sequence. However, by modifying the reverse paths via planning, planners create an irrevocable mismatch between the uniformly random denoising paths assumed during