🤖 AI Summary
Existing authorization mechanisms struggle to meet the governance demands of autonomous agents, particularly regarding permission inheritance, dynamic scoping, and recursive delegation. This work proposes a composable governance framework that, for the first time, formalizes recursive delegation, contextual boundaries, and dynamic scoping as composable governance primitives. It introduces a resource scoping decay mechanism to model delegation relationships through contractual constructs. Built upon a relational authorization model, the framework defines stackable composition operators that formally express delegation types and permission decay rules while remaining compatible with mainstream identity and access management (IAM) systems. Theoretical analysis and empirical evaluation demonstrate that the framework effectively supports dynamic authorization governance in complex agent systems without compromising accountability.
📝 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. Agentic AI demands richer authorization semantics: agents must inherit and delegate permissions, act under time-limited authority, and coordinate through shared protocols. Existing Identity and Access Management (IAM) systems fail to fully capture this notion of agency, lacking mechanisms for recursive delegation, contextual boundaries, and dynamic scoping as executable governance primitives. Unlike access delegation standards such as OAuth 2.0, we treat delegation as a contractual term rather than merely a static token-based consent credential. This paper proposes a compositional governance framework that introduces primitives indispensable for agentic AI. We define types of delegation and their permissions and accountability implications, and we introduce a notion of resource scope attenuation to bound agentic access envelopes. These concepts are expressed as general relational definitions that can be composed into existing authorization domains (e.g., financial systems). To operationalize this composition, we define a compositional operator that overlays new agentic semantics, such as recursive delegation chains, onto existing relational policies without rewriting them. We substantiate this framework through formal proofs and empirical evaluation, showing that it provides a formal yet practical foundation for accountable authorization in agentic AI systems.