Skip to content
Agents

Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment.

arXiv:2610.08670v2 Announce Type: replace-cross Abstract: An agent that can say an action is wrong and then take it anyway is a different failure from one that does not know better, and evaluations of stated values cannot see it. We ask how often open models a

arXiv cs.AIResearch source·