Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL [R]

Autoregressive LLM world models factorize next-state generation left-to-right, preventing them from conditioning on globally interdependent anchors (tool schemas, trailing status fields, expected outcomes) and yielding prefix-consistent but globally incoherent rollouts. MDLMs' any-order denoising ob