G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm
Small language model (SLM) agents need safety controls that track consequences across tool calls with little monitoring overhead. A private read, for example, becomes a leak when a later action sends that data outside the system. We introduce CARB (Conformal Agent Risk Budget), which calibrates when to stop an agent us...
Zi-Jun Yu, Yu-Tong Gu, Vahid Partovi Nia et al.
· 0 citations