AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rosser, J, Foerster, Jakob
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Neural and Evolutionary Computing 68T42, 68T50 I.2.11
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.00757