Separating Capability from Permission: A Governance Framework for Agentic AI Autonomy Levels

• URL: http://arxiv.org/abs/2607.23438v1
• Date: Sun, 26 Jul 2026 03:32:13 GMT
• Title: Separating Capability from Permission: A Governance Framework for Agentic AI Autonomy Levels
• Abstract summary: This paper introduces a governance framework that separates Allowed Autonomy Levels (AAL) and Autonomous Capability Levels (ACL)<n>AAL defines the degree of autonomy an AI agent is authorized to exercise given risk, oversight, and accountability considerations.<n>We present a structured set of autonomy levels spanning reactive execution, decision support, supervised action, goal-directed autonomy, and delegated operational authority.
• Score: 15.361996125107979
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As AI systems increasingly exhibit agentic behavior, discussions of autonomy often conflate what systems are technically capable of doing with what they should be permitted to do in practice. This paper introduces a governance framework that explicitly separates Allowed Autonomy Levels (AAL), which define the degree of autonomy an AI agent is authorized to exercise given risk, oversight, and accountability considerations, from Autonomous Capability Levels (ACL), which characterize an agent's inherent technical abilities. We present a structured set of autonomy levels spanning reactive execution, decision support, supervised action, goal-directed autonomy, and delegated operational authority, and describe how control, reversibility, and accountability change as autonomy increases. To operationalize this framework, we propose a risk-aware decision process for assigning allowed autonomy, analyze how risk and accountability evolve across autonomy levels, and demonstrate its application through a deployed enterprise data engineering agent, illustrating how a system assessed at a high capability level can be deliberately constrained to a lower allowed autonomy based on risk, reversibility, and organizational readiness. By distinguishing authorization from capability, this work provides practical guidance for the design, deployment, and governance of Agentic AI systems.

Related papers

• Assessing Company Contributions to Societal Resilience: Extending the Societal Capacity Assessment Framework to Agentic AI [40.57385775451146]
  This paper adapts the indicator-based Societal Capacity Assessment Framework to measure how a company's deployment decisions contribute to societal resilience.<n>Our procedure has two steps: a conceptual step in which we design a suite of indicators that define what SCAF's vulnerability, coping, and adaptive capacities mean when assessing a company's AI deployment decisions; and a measurement step in which we apply this framework in a structured assessment of public-facing Microsoft documents.
  arXiv  Detail & Related papers  (2026-08-27T15:21:41Z)
• Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems [0.0]
  This paper explores the architectural vulnerability of unbounded autonomy.<n>We instantiate this theory via the SMARt model, a four-layer framework featuring Stable, Meta-cognitive, Assisted, and Regulated states.<n>We conclude that formalizing failure management within the autonomy lifecycle is a crucial step toward realizing reliable and governed artificial intelligence.
  arXiv  Detail & Related papers  (2026-05-26T19:49:23Z)
• Agentic Business Process Management: A Research Manifesto [26.864255980822325]
  Agentic Business Process Management (APM) is an extension of Business Process Management (BPM)<n>From a management perspective, APM represents a paradigm shift from the traditional process view of the business process.<n>We introduce the core abstractions and architectural elements required to realize APM systems.
  arXiv  Detail & Related papers  (2026-03-19T13:52:17Z)
• From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents [36.1914922430313]
  We present a taxonomy of threats spanning cognitive manipulation, physical environment disruption, and multi-agent systemic failures.<n>The findings aim to guide the development of multilayered, autonomy-aware defense architectures for trustworthy AI agent systems.
  arXiv  Detail & Related papers  (2026-03-08T06:45:28Z)
• Assured Autonomy: How Operations Research Powers and Orchestrates Generative AI Systems [18.881800772626427]
  We argue generative models can be fragile in operational domains unless paired with mechanisms that provide feasibility, robustness to distribution shift, and stress testing.<n>We develop a conceptual framework for assured autonomy grounded in operations research.<n>These elements define a research agenda for assured autonomy in safety-critical, reliability-sensitive operational domains.
  arXiv  Detail & Related papers  (2025-12-30T04:24:06Z)
• Towards Responsible and Explainable AI Agents with Consensus-Driven Reasoning [4.226647687395254]
  This paper presents a Responsible(RAI) and Explainable(XAI) AI Agent Architecture for production-grade agentic based on multi-model consensus and reasoning-layer governance.<n>In the proposed design, a consortium of heterogeneous LLM and VLM agents independently generates candidate outputs from a shared input context.<n>A dedicated reasoning agent then performs structured consolidation across these outputs, enforcing safety and policy constraints, mitigating hallucinations and bias, and producing auditable, evidence-backed decisions.
  arXiv  Detail & Related papers  (2025-12-25T14:49:25Z)
• Governable AI: Provable Safety Under Extreme Threat Models [31.36879992618843]
  We propose a Governable AI (GAI) framework that shifts from traditional internal constraints to externally enforced structural compliance.<n>The GAI framework is composed of a simple yet reliable, fully deterministic, powerful, flexible, and general-purpose rule enforcement module (REM); governance rules; and a governable secure super-platform (GSSP) that offers end-to-end protection against compromise or subversion by AI.
  arXiv  Detail & Related papers  (2025-08-28T04:22:59Z)
• A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents [45.53643260046778]
  Recent advances in large language models (LLMs) have catalyzed the rise of autonomous AI agents.<n>These large-model agents mark a paradigm shift from static inference systems to interactive, memory-augmented entities.
  arXiv  Detail & Related papers  (2025-06-30T13:34:34Z)
• Levels of Autonomy for AI Agents [9.324309359500198]
  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.
  arXiv  Detail & Related papers  (2025-06-14T12:14:36Z)
• 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)
• Artificial Intelligence in Government: Why People Feel They Lose Control [44.99833362998488]
  The use of Artificial Intelligence in public administration is expanding rapidly.<n>While AI promises greater efficiency and responsiveness, its integration into government functions raises concerns about fairness, transparency, and accountability.<n>This article applies principal-agent theory to AI adoption as a special case of delegation.
  arXiv  Detail & Related papers  (2025-05-02T07:46:41Z)
• 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)
• Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples [70.84093873437425]
  This paper introduces the Accountable Offline Controller (AOC) that employs the offline dataset as the Decision Corpus. AOC operates effectively in low-data scenarios, can be extended to the strictly offline imitation setting, and displays qualities of both conservation and adaptability. We assess AOC's performance in both simulated and real-world healthcare scenarios, emphasizing its capability to manage offline control tasks with high levels of performance while maintaining accountability.
  arXiv  Detail & Related papers  (2023-10-11T17:20:32Z)
• Assurance for Autonomy -- JPL's past research, lessons learned, and future directions [56.32768279109502]
  Autonomy is required when a wide variation in circumstances precludes responses being pre-planned. Mission assurance is a key contributor to providing confidence, yet assurance practices honed over decades of spaceflight have relatively little experience with autonomy. Researchers in JPL's software assurance group have been involved in the development of techniques specific to the assurance of autonomy.
  arXiv  Detail & Related papers  (2023-05-16T18:24:12Z)
• Learning to Optimize Autonomy in Competence-Aware Systems [32.3596917475882]
  We propose an introspective model of autonomy that is learned and updated online through experience. We define a competence-aware system (CAS) that explicitly models its own proficiency at different levels of autonomy and the available human feedback. We analyze the convergence properties of CAS and provide experimental results for robot delivery and autonomous driving domains.
  arXiv  Detail & Related papers  (2020-03-17T14:31:45Z)

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.