1
How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation
研究揭示LLM搜索代理易受网页内容操控影响，测量“背书漏洞”的严重性，关乎AI安全底线。
arXiv:2606.16821v1 Announce Type: new Abstract: Large language model (LLM)-based search agents synthesize open-web content into actionable recommendat…