Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement 文章

ArXiv CS.CL2026-05-27NEWSen作者: Dingwei Chen, Zefang Zong, Zhipeng Ma, Leo Luo, Yang Li, Chengming Li, Peng Chen, Jie Jiang
查看原文 →
关系图谱

Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement · 相关技术

相关技术

ODE远程代码执行（RCE）reward hackingreinforcement learningToolsSynthetic Aperture RadarStanParts-of-Speech (POS) tagsPROBEPPROWLNATLMMLLM-based agentIMUHISForFFIEFIAgentic RLARGANNAgentAPIICE