Levels of Autonomy for AI Agents
This work addresses the challenge of balancing autonomy and control in AI agents for developers and users, but it is incremental as it builds on existing concepts without introducing new methods or data.
The paper tackles the problem of calibrating appropriate autonomy levels for AI agents by proposing a framework with five escalating levels defined by user roles, aiming to contribute to responsibly deployed AI agents.
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.