作者位次 #6/10ICLR 2026Poster
From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones
Lifan Yuan · Weize Chen · Yuchen Zhang · Ganqu Cui · Hanbin Wang · Ziming You · Ning Ding · Zhiyuan Liu · Maosong Sun · Hao Peng
强化学习与后训练OpenReview