arXiv:2506.22276 · v2

Artificial Intelligent Disobedience: Rethinking the Agency of Our Artificial Teammates

首次提交 2025-06-27 22:45

版本更新 2026-11-03 10:04

雷达观测 2026-11-04 23:40

摘要

Artificial intelligence has made remarkable strides in recent years, achieving superhuman performance across a wide range of tasks. Yet despite these advances, most cooperative AI systems remain rigidly obedient, designed to follow human instructions without question and conform to user expectations, even when doing so may be counterproductive or unsafe. This paper argues for expanding the agency of AI teammates to include \textit{intelligent disobedience}, empowering them to make meaningful and autonomous contributions within human-AI teams. It introduces a scale of AI agency levels and uses representative examples to highlight the importance and growing necessity of treating AI autonomy as an independent research focus in cooperative settings. The paper then explores how intelligent disobedience manifests across different autonomy levels and concludes by proposing initial boundaries and considerations for studying disobedience as a core capability of artificial agents.

作者备注：Extended version of the AI Magazine publication

期刊信息：AI Magazine. 2025;46:e70011