#artificial intelligence
Jun 2026
On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout and schedules the teacher's intervention probability along a curriculum that decays to zero is proposed.
Gengsheng Li, Mao Zheng, Ming-Yang Song et al.
· arXiv.org · 24 citations
· ⚡3