Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization
Outcome-based reinforcement learning provides verified feedback for language-model agents, but assigns trajectory-level advantage uniformly to all decisions, yielding coarse credit over long-horizon interactions. On-policy self-distillation offers finer supervision by re-evaluating sampled behavior with privileged information (PI) available only during training. However, fine-grained supervision…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
