BARC-Bench: Benign Asks, Risky Consequences
arXiv:2610.32024v1 Announce Type: new Abstract: Task instructions from users for agents are inherently underspecified, especially regarding safety boundaries--creating behavioral risks. To study these risks, we introduce BARC-Bench, a...
Read more: https://arxiv.org/abs/2610.32024
Scan with your phone
Scan with your phone