Which artificial intelligence (AI) systems are agents? To answer this question, I propose a multidimensional account of agency. According to this account, a system's agency profile is jointly determined by its level of goal-directedness and autonomy as well as is abilities for directly impacting the surrounding world, long-term planning and acting for reasons. Rooted in extant theories of agency, this account enables fine-grained, nuanced comparative characterizations of artificial agency. I show that this account has multiple important virtues and is more informative than alternatives. More speculatively, it may help to illuminate two important emerging questions in AI ethics: 1. Can agency contribute to the moral status of non-human beings, and how? 2. When and why might AI systems exhibit power-seeking behaviour and does this pose an existential risk to humanity?

中文翻译：

---

了解人工代理

哪些人工智能 (AI) 系统是代理？为了回答这个问题，我提出了对代理的多维解释。根据这种说法，一个系统的代理形象是由其目标导向性和自主性水平以及直接影响周围世界、长期规划和有理行动的能力共同决定的。这一解释植根于现有的代理理论，能够对人工代理进行细粒度、细致入微的比较表征。我表明该帐户具有多种重要优点，并且比其他帐户提供更多信息。更具推测性的是，它可能有助于阐明人工智能伦理中两个重要的新兴问题：1.代理能否对非人类的道德地位做出贡献，以及如何做出贡献？ 2. 人工智能系统何时以及为何会表现出寻求权力的行为，这是否会对人类构成生存风险？