# RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning > Source: > Published: 2026-09-18 03:00:08+00:00 Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivates self on-policy distillation (OPD) to supply dense token-level supervision from a self-teacher with privileged task skills, letting a skill-free student internalize them. This rec