Levels of Autonomy for AI Agents

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Feng, K. J. Kevin, McDonald, David W., Zhang, Amy X.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911079069646848
author Feng, K. J. Kevin
McDonald, David W.
Zhang, Amy X.
author_facet Feng, K. J. Kevin
McDonald, David W.
Zhang, Amy X.
contents Autonomy is a double-edged sword for AI agents, simultaneously unlocking transformative possibilities and serious risks. How can agent developers calibrate the appropriate levels of autonomy at which their agents should operate? We argue that an agent's level of autonomy can be treated as a deliberate design decision, separate from its capability and operational environment. In this work, we define five levels of escalating agent autonomy, characterized by the roles a user can take when interacting with an agent: operator, collaborator, consultant, approver, and observer. Within each level, we describe the ways by which a user can exert control over the agent and open questions for how to design the nature of user-agent interaction. We then highlight a potential application of our framework towards AI autonomy certificates to govern agent behavior in single- and multi-agent systems. We conclude by proposing early ideas for evaluating agents' autonomy. Our work aims to contribute meaningful, practical steps towards responsibly deployed and useful AI agents in the real world.
format Preprint
id arxiv_https___arxiv_org_abs_2506_12469
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Levels of Autonomy for AI Agents
Feng, K. J. Kevin
McDonald, David W.
Zhang, Amy X.
Human-Computer Interaction
Artificial Intelligence
Autonomy is a double-edged sword for AI agents, simultaneously unlocking transformative possibilities and serious risks. How can agent developers calibrate the appropriate levels of autonomy at which their agents should operate? We argue that an agent's level of autonomy can be treated as a deliberate design decision, separate from its capability and operational environment. In this work, we define five levels of escalating agent autonomy, characterized by the roles a user can take when interacting with an agent: operator, collaborator, consultant, approver, and observer. Within each level, we describe the ways by which a user can exert control over the agent and open questions for how to design the nature of user-agent interaction. We then highlight a potential application of our framework towards AI autonomy certificates to govern agent behavior in single- and multi-agent systems. We conclude by proposing early ideas for evaluating agents' autonomy. Our work aims to contribute meaningful, practical steps towards responsibly deployed and useful AI agents in the real world.
title Levels of Autonomy for AI Agents
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2506.12469