arXivWeijie Ren, Yanwen Zhang, Hao Li, Zhuolin Qi, Hengyi Zhang, Naibo WangWed, Sep 30, 2026, 7:56 AM PDT
score 16.9
Training AI students with an expert role as coach
Original: OPSRD: On-Policy Self-Role Distillation
Source: arxiv.org ↗
Writing ELI5 summary…