Dynamic Dual-Granularity Skill Bank for Agentic RL 文章

ArXiv CS.AI2026-05-26NEWSen作者: Songjun Tu, Chengdong Xu, Qichao Zhang, Yaocheng Zhang, Xiangyuan Lan, Linjing Li, Dong Li, Dongbin Zhao
查看原文 →
关系图谱

Dynamic Dual-Granularity Skill Bank for Agentic RL · 相关技术

相关技术

SkillORMPLAevalStraight-Through EstimatorStanReferring expression comprehension (REC)Parts-of-Speech (POS) tagsPPOMECGranular Alignment ParadigmGANForEFICISAgentic RLANNAgent