SOURCE-LINKED INTELLIGENCE

Cognitive Admission Control: Risk-Conditioned Assurance for Consequential Actions in Agentic Distributed Systems

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

In agentic distributed systems, an agent may be authorized to mutate external infrastructure while lacking evidence that the mutation is ready to execute. Cognitive Admission Control (CAC) makes this evidence requirement explicit. A policy maps a typed action and its modeled risk to assurance obligations specifying predicates, evidence classes, scope, freshness, and witness-set constraints. A deterministic evaluator distinguishes satisfied, violated, and unresolved obligations; unresolved conditions produce targeted evidence-acquisition requests. Successful admission produces a certificate bin

Read original source ↗ Open in workspace

recordType

paper

region

Global