Information Retrieval Induced Safety Degradation in AI Agents

Cheng Yu, Benedikt Stroebl, Diyi Yang, Orestis Papakyriakopoulos. Information Retrieval Induced Safety Degradation in AI Agents. In Danielle Belgrave, Cheng Zhang 0005, Laura N. Montoya, Hsuan-Tien Lin, Razvan Pascanu, Piotr Koniusz, Marzyeh Ghassemi, Nancy Chen, Iván Vladimir Meza Ruíz, Arturo Loaiza-Bonilla, editors, Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, NeurIPS 2025, San Diago, CA, USA, December 2-7, 2025 / Mexico City, Mexico, November 30 - December 5, 2025. 2025. [doi]

Authors

Cheng Yu

This author has not been identified. Look up 'Cheng Yu' in Google

Benedikt Stroebl

This author has not been identified. Look up 'Benedikt Stroebl' in Google

Diyi Yang

This author has not been identified. Look up 'Diyi Yang' in Google

Orestis Papakyriakopoulos

This author has not been identified. Look up 'Orestis Papakyriakopoulos' in Google