Positive-Unlabeled Learning for Agent Safety False Alarm Auditing
Safety monitors help safeguard language-model agents interacting with external tools and environments, but conservative monitoring can generate many false alarms, consuming extensive review resources and weakening trust in alerts. Because false and genuine alarms often remain interleaved in native monitor scores, obtai...
Xi-Chen Yan, Chong-Yang Gao, Ke-Zhen Chen et al.
· 0 citations