Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Khattar, Vanshaj, Rashid, Md Rafi ur, Choudhury, Moumita, Liu, Jing, Koike-Akino, Toshiaki, Jin, Ming, Wang, Ye
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2603.15417