Home » Authors » Param Biyani, Sebastien Luyasu, Cedric Potvliege, Divij Chawla, Elliott Thornley, Christos Ziakas

Param Biyani, Sebastien Luyasu, Cedric Potvliege, Divij Chawla, Elliott Thornley, Christos Ziakas

Public reference bibliography and cataloged PDF materials authored or published by Param Biyani, Sebastien Luyasu, Cedric Potvliege, Divij Chawla, Elliott Thornley, Christos Ziakas.

Found 1 document(s) Page 1 of 1

ShutdownMod: Turning Any Trajectory into a Shutdown Evaluation

Year: 2026 • Source: arxiv.org • Listed PDF

Theory and experiments suggest that capable AI agents may resist shutdown. Existing shutdown evaluations are informative but limited in coverage and vulnerable to evaluation awareness. We introduce ShutdownMod, a method ...