Large reasoning models are autonomous jailbreak agents
Thilo Hagendorff, Erik Derner, Nuria Oliver
Nature Communications, 17(1), 2026.
Abstract
Links
BibTeX
@article{Hagendorff_2026,
title = {Large reasoning models are autonomous jailbreak agents},
volume = {17},
issn = {2041-1723},
url = {http://dx.doi.org/10.1038/s41467-026-69010-1},
doi = {10.1038/s41467-026-69010-1},
number = {1},
journal = {Nature Communications},
publisher = {Springer Science and Business Media LLC},
author = {Hagendorff, Thilo and Derner, Erik and Oliver, Nuria},
year = {2026}
}