Predicting Privileged Information Effectiveness for On-Policy Self-Distillation
This work systematically evaluates 16 PI configurations across three multi-turn agentic benchmarks and three student models that vary in scale and reasoning mode and finds that PI effectiveness depends on its content, generation source, and the student model.
Kai-Jian Zou, Emiliano Penaloza, MohammadHossein Rezaei et al.
· 0 citations