Auditing medical multi-agent AI reveals risks of false consensus 文章

ArXiv CS.CL2026-05-28NEWSen作者: Yinghao Zhu, Lei Gu, Zixiang Wang, Haoran Sang, Dehao Sui, Wen Tang, Lan Mi, Yasha Wang, Junyi Gao, Liang Yao, Tianfan Fu, Ewen Harrison, Lequan Yu, Liantao Ma
大语言模型
查看原文 →
关系图谱

Auditing medical multi-agent AI reveals risks of false consensus · 相关技术

相关技术

ODEPLALLMlanguage model企业通用语义标准safetymulti-agent systemsexecevaldivide-and-conquer partitioningStraight-Through EstimatorSULSSESPASEMSAFEReferring expression comprehension (REC)PPOORMMulti-Agentlarge language modelsForKEPTEDADiTDAGCLICISARGANNAgent