When Privileged Guidance Misaligns: State-Matched Routing and Contextualized Self-Distillation for Multi-Turn Agents

arXiv:2608.05219v1 Announce Type: new Abstract: Privileged onpolicy distillation provides dense supervision for multiturn agents by allowing a synchronized teacher to rescore the student's response at every turn with access to trainingonly references, such as successful trajectories.