Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive Screening
IntermediateZhenxiong Yu, Zhi Yang et al.Feb 5arXiv
Before this work, AI agents often stopped to run safety checks at every single step, which made them slow and still easy to trick in sneaky ways.
#Intrinsic Risk Sensing#Event-driven defense#Hierarchical Adaptive Screening