OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vijayvargiya, Sanidhya, Soni, Aditya Bharat, Zhou, Xuhui, Wang, Zora Zhiruo, Dziri, Nouha, Neubig, Graham, Sap, Maarten
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2507.06134