Author name: Martin Odersky, Yaoyu Zhao, Yichen Xu, Oliver Bra\v{c}evac, Cao Nguyen Pham

arXiv:2603.00991v2 Announce Type: replace
Abstract: AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prom…