Levels of Autonomy for AI Agents

• URL: http://arxiv.org/abs/2506.12469v2
• Date: Mon, 28 Jul 2025 16:25:18 GMT
• Title: Levels of Autonomy for AI Agents
• Authors: K. J. Kevin Feng, David W. McDonald, Amy X. Zhang,
• Abstract summary: We argue that an agent's level of autonomy can be treated as a deliberate design decision, separate from its capability and operational environment.<n>We define five levels of escalating agent autonomy, characterized by the roles a user can take when interacting with an agent.<n>We highlight a potential application of our framework towards AI autonomy certificates to govern agent behavior in single- and multi-agent systems.
• Score: 9.324309359500198
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience [71.82719117238307]
  We propose SEAgent, an agentic self-evolving framework enabling computer-use agents to evolve through interactions with unfamiliar software.<n>We validate the effectiveness of SEAgent across five novel software environments within OS-World.<n>Our approach achieves a significant improvement of 23.2% in success rate, from 11.3% to 34.5%, over a competitive open-source CUA.
  arXiv  Detail & Related papers  (2025-08-06T17:58:46Z)
• Agentic Web: Weaving the Next Web with AI Agents [109.13815627467514]
  The emergence of AI agents powered by large language models (LLMs) marks a pivotal shift toward the Agentic Web.<n>In this paradigm, agents interact directly with one another to plan, coordinate, and execute complex tasks on behalf of users.<n>We present a structured framework for understanding and building the Agentic Web.
  arXiv  Detail & Related papers  (2025-07-28T17:58:12Z)
• From Autonomy to Agency: Agentic Vehicles for Human-Centered Mobility Systems [0.0]
  This paper presents a systems-level framework to characterize agentic vehicles (AgVs)<n>AgVs integrate agentic AI to reason, adapt, and interact within complex environments.<n>The paper concludes by identifying key challenges in the development and governance of AgVs.
  arXiv  Detail & Related papers  (2025-07-07T13:34:49Z)
• Toward a Theory of Agents as Tool-Use Decision-Makers [89.26889709510242]
  We argue that true autonomy requires agents to be grounded in a coherent epistemic framework that governs what they know, what they need to know, and how to acquire that knowledge efficiently.<n>We propose a unified theory that treats internal reasoning and external actions as equivalent epistemic tools, enabling agents to systematically coordinate introspection and interaction.<n>This perspective shifts the design of agents from mere action executors to knowledge-driven intelligence systems, offering a principled path toward building foundation agents capable of adaptive, efficient, and goal-directed behavior.
  arXiv  Detail & Related papers  (2025-06-01T07:52:16Z)
• Measuring AI agent autonomy: Towards a scalable approach with code inspection [8.344207672507334]
  We introduce a code-based assessment of autonomy that eliminates the need to run an AI agent to perform specific tasks.<n>We demonstrate this approach with the AutoGen framework and select applications.
  arXiv  Detail & Related papers  (2025-02-21T04:58:40Z)
• YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks [16.443149180969776]
  Augmented Reality (AR) head worn devices can uniquely improve the user experience of solving procedural day-to-day tasks.<n>Such AR capabilities can help AI Agents see and listen to actions that users take which can relate to multimodal capabilities of human users.<n>Proactivity of AI Agents on the other hand can help the human user detect and correct any mistakes in agent observed tasks.
  arXiv  Detail & Related papers  (2025-01-16T08:06:02Z)
• Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents [64.75036903373712]
  Proposer-Agent-Evaluator is a learning system that enables foundation model agents to autonomously discover and practice skills in the wild.<n>At the heart of PAE is a context-aware task proposer that autonomously proposes tasks for the agent to practice with context information.<n>The success evaluation serves as the reward signal for the agent to refine its policies through RL.
  arXiv  Detail & Related papers  (2024-12-17T18:59:50Z)
• Agent-as-a-Judge: Evaluate Agents with Agents [61.33974108405561]
  We introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is an organic extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving process. We present DevAI, a new benchmark of 55 realistic automated AI development tasks.
  arXiv  Detail & Related papers  (2024-10-14T17:57:02Z)
• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence [79.5316642687565]
  Existing multi-agent frameworks often struggle with integrating diverse capable third-party agents. We propose the Internet of Agents (IoA), a novel framework that addresses these limitations. IoA introduces an agent integration protocol, an instant-messaging-like architecture design, and dynamic mechanisms for agent teaming and conversation flow control.
  arXiv  Detail & Related papers  (2024-07-09T17:33:24Z)
• CACA Agent: Capability Collaboration based AI Agent [18.84686313298908]
  We propose CACA Agent (Capability Collaboration based AI Agent) using an open architecture inspired by service computing. CACA Agent integrates a set of collaborative capabilities to implement AI Agents, not only reducing the dependence on a single LLM. We present a demo to illustrate the operation and the application scenario extension of CACA Agent.
  arXiv  Detail & Related papers  (2024-03-22T11:42:47Z)
• Consent as a Foundation for Responsible Autonomy [15.45515784064555]
  This paper focuses on a dynamic aspect of responsible autonomy, namely, to make intelligent agents be responsible at run time. It considers settings where decision making by agents impinges upon the outcomes perceived by other agents.
  arXiv  Detail & Related papers  (2022-03-22T02:25:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.