Seeing is Believing? Evaluating Vision-Language Model Susceptibility in Agent-to-Agent Multimodal Persuasion 文章

ArXiv CS.CL2026-06-05NEWSen作者: Haoyi Qiu, Yilun Zhou, Pranav Narayanan Venkit, Kung-Hsiang Huang, Jiaxin Zhang, Nanyun Peng, Chien-Sheng Wu
查看原文 →
关系图谱

Seeing is Believing? Evaluating Vision-Language Model Susceptibility in Agent-to-Agent Multimodal Persuasion · 相关技术

相关技术

function-callingVision-Language ModelsAgent-to-Agent