2604.14922v1
CC BY 4.0
Alibaba / Qwen Team
LongAct:利用內在激活模式實現長上下文強化學習
LongAct Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
Bowen Ping, Zijun Chen, Tingfeng Hui, Qize Yu, Chenxuan Li, Junchi Yan, Baobao Chang
LLMLong ContextReinforcement LearningActivationSparse UpdateGRPO
Teds Lin 許願