AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions 文章

ArXiv CS.AI2026-05-26NEWSen作者: Jingwei Sun, Jianing Zhu, Yuanyi Li, Tongliang Liu, Xia HU, Bo Han
大语言模型
查看原文 →
关系图谱

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions · 相关技术

相关技术

LLMginMultimodal Large Language Models (MLLMs)ODElanguage model远程代码执行（RCE）研究法辛烷值多模态rsaexecevaldivide-and-conquer partitioningadversarial modelSynthetic Aperture RadarStanReferring expression comprehension (REC)PETOWSLMMlarge language modelsForENAComputer UseARGANNAgentGitiOS