Shutdownable Agents through POST-Agency
Artificial Intelligence
2026-01-06 v3
Abstract
Many fear that future artificial agents will resist shutdown. I present an idea - the POST-Agents Proposal - for ensuring that doesn't happen. I propose that we train agents to satisfy Preferences Only Between Same-Length Trajectories (POST). I then prove that POST - together with other conditions - implies Neutrality+: the agent maximizes expected utility, ignoring the probability distribution over trajectory-lengths. I argue that Neutrality+ keeps agents shutdownable and allows them to be useful.
Cite
@article{arxiv.2505.20203,
title = {Shutdownable Agents through POST-Agency},
author = {Elliott Thornley},
journal= {arXiv preprint arXiv:2505.20203},
year = {2026}
}