نسخة أولية وصول مفتوح
Stochastic Teacher Intervention for Agentic On-Policy Distillation
On-policy distillation (OPD) efficiently transfers capabilities from a stronger teacher to a student language model through dense token-level supervision on student-generated rollouts and has shown promise on complex tasks such as mathematical reasoning. However, in multi-turn agentic tasks, student decisions shape sub …