X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems
Personal agents increasingly connect to services across the web and applications by using tools. As the effects of their actions accumulate and interact across services, unintended or harmful outcomes can arise when agents fulfill benign user requests. Proactively identifying these compositional failures requires syste...
Yeonsung Jung, Zhi-Yuan Wang, Zi-Fan Wang et al.
· 0 citations