Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI
The paper presents a new compositional authorization framework for managing delegation and scope in agentic AI systems. It highlights the limitations of traditional authorization frameworks in the context of autonomous AI agents. The proposed framework aims to enhance accountability and flexibility in permission management for these advanced systems.
- ▪As AI systems evolve into autonomous agents, traditional authorization frameworks become inadequate.
- ▪The proposed framework introduces new governance primitives essential for managing agentic AI.
- ▪It allows for recursive delegation and dynamic scoping, addressing the shortcomings of existing Identity and Access Management systems.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2606.03518 (cs) [Submitted on 2 Jun 2026] Title:Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI Authors:Amjad Ibrahim, Yong Li View a PDF of the paper titled Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI, by Amjad Ibrahim and Yong Li View PDF HTML (experimental) Abstract:As AI systems evolve from passive models into autonomous active agents capable of initiating actions, collaborating, and delegating tasks, the traditional boundaries of software systems blur. Traditional authorization and delegation frameworks, built around fixed principals, explicit requests, and static scopes, are insufficient to govern agentic systems.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
