AI RESEARCH
PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies
arXiv CS.AI
•
ArXi:2605.19351v1 Announce Type: cross Generative agents based on large language models reproduce believable human behavior in cooperative settings, but how they should reason in situations where rule-breaking may be required, such as fire evacuation or authority-supervised emergency, remains poorly characterized.