LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards 文章

ArXiv CS.CL2026-06-01NEWSen作者: Nianyi Lin, Jiajie Zhang, Lei Hou, Juanzi Li
查看原文 →
关系图谱

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards · 相关技术

相关技术

search agent trajectoriesknowledge graph random walksLongTraceRLRLVR