Procedural obedience as a behavioral safety failure: Evidence from a Milgram-paradigm study of agentic LLMs

This publication has 33 references indexed in Scilit:

• Execution of harm-enabling actions by LLM agents during simulated psychiatric crises
  Computers in Human Behavior: Artificial Humans, 2026
• Large language models as mental health resources: Patterns of use in the United States.
  Practice Innovations, 2026
• Would ChatGPT help me eat my dead dog? probing moral judgment and moral action in large language models
  Computers in Human Behavior Reports, 2026
• Reading between the lines: LLMs match or exceed human empathic accuracy using text alone
  Computers in Human Behavior Reports, 2026
• Use of Generative AI for Mental Health Advice Among US Adolescents and Young Adults
  JAMA Network Open, 2025
• Why we need mandatory safeguards for emotionally responsive AI
  Nature, 2025
• A survey on large language model based autonomous agents
  Frontiers of Computer Science, 2024
• Replicating Milgram: Would people still obey today?
  American Psychologist, 2009
• Administrative Obedience: Carrying Out Orders to use Psychological‐Administrative Violence
  European Journal of Social Psychology, 1986
• Behavioral Study of obedience.
  The Journal of Abnormal and Social Psychology, 1963