arXiv cs.CL
· Papers
Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance
arXiv:2608.12323v1 Announce Type: new Abstract: Specifying a penalty can paradoxically convert a legal obligation into a cost-benefit calculation that favors violation. We demonstrate that this enforcement information paradox systematically occurs in AI agents. While most AI safety evaluations test whether models fail,