TreeOPSD: A Tree-Aware Posterior Self-Distillation Framework for Long-Horizon Agentic Reinforcement Learning

TreeOPSD proposes a critic-free, tree-aware posterior self-distillation framework for long-horizon agentic reinforcement learning. It treats each interaction turn as a tree node, branches alternative continuations from shared prefixes, and recursively backs up terminal rewards to obtain implicit turn-level credit.