Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games 文章

ArXiv CS.AI2026-05-26NEWSen作者: Yidong He, Yutao Lai, Pengxu Yang, Jiarui Gan, Jiexin Wang, Yi Cai, Mengchen Zhao
大语言模型
查看原文 →
关系图谱

Strat-Reasoner: Reinforcing Strategic Reasoning of LLMs in Multi-Agent Games · 相关技术

相关技术

Large language modelSSELLMODEPLAlanguage model通用表达式语言递归自我改进远程代码执行（RCE）信用分配reinforcement learningevalStraight-Through EstimatorReferring expression comprehension (REC)Parts-of-Speech (POS) tagsPPRMulti-AgentLMMHISForDiTARGANNAgent