Learning from Think-Mode Advantage via On-Policy Distillation
Explicit intermediate reasoning gives large language models (LLMs) a stronger problem-solving mode. We study learning from this think-mode advantage via on-policy distillation (OPD). OPD preserves student-generated trajectories and provides dense token-level teacher targets at student-visited prefixes. Privileged reaso...
Wan-Qi Ren, Jian-Xiang Wang, Dan-Xuan Liu et al.
· 0 citations