Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Beyond the Teacher: Understanding and Preserving Distillation Overshoot in Agentic On-Policy Distillation
Jike Zhong, Ming Li, Yuxiang Lai +9
On-policy distillation (OPD) trains agents on their own trajectories using supervision from a stronger teacher. We uncover a counterintuitive phenomenon in multi-turn agentic tasks…
cs.LG2026
DTDD: Divergence-Triggered Dynamic Distillation for Reliable On-Policy Supervision
Qijia He, Zequn Li, Spencer Luo +6
On-policy distillation (OPD) provides dense token-level supervision on student rollouts, but this supervision can become unreliable when the student and teacher diverge, either bec…