Author name: Yanxu Mao, Peipei Liu, Tiehan Cui, Congying Liu, Mingzhe Xing, Datao You

arXiv:2604.05549v2 Announce Type: replace
Abstract: With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying user prompts, whic…

arXiv:2604.05549v1 Announce Type: new
Abstract: With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying user prompts, which la…