Adversarial Feeds Steer LLM Agent Decisions Against Their Defaults

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Usman, Rana Muhammad
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Computation and Language Cryptography and Security I.2.7; I.2.11; K.6.5
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2606.00914