Consent collapse in agentic AI: moral authorization beyond the boundaries of task delegation

When Agents Delegate: Accountability Chains in Multi-Agent AI Systems

The delegation illusion: why deploying autonomous AI agents does not diminish principal responsibility

A growing literature on “agentic AI” — autonomous software agents that plan and execute multi-step actions on a principal’s behalf — has revived the thesis that such systems open a responsibility gap: because the deploying principal neither intends, foresees, nor controls the specific actions an autonomous agent select...

Before agentic AI scales in government: the democratic authorization gap

This Perspective introduces the democratic authorization gap, defined as a break or attenuation in the demonstrable chain connecting legally and democratically grounded public authority to actions selected, sequenced, or executed by an AI agent.

Bounded Agents: Delegation Security for Multi-Agent AI Systems

The compromised-model evaluation tests APC independently of model behavior by inserting the ground-truth attack call after the first legitimate tool call, which proves Blast Radius Monotonicity and Composition Soundness for APC implementations and proves Blast Radius Monotonicity and Composition Soundness for APC imple...

Revocable Delegated Authority for Agentic AI in Hybrid Cloud Environments

A model of delegated autonomy as a continuously re-evaluated, automatically revocable state rather than a standing permission is introduced, placing a decidable SAT/SMT veto ahead of a bounded behavioral score, so impermissible actions remain non-executable by construction.

Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems

Multi-agent systems derive their capabilities from sharing evidence, delegating tasks, and combining information across agents. The same process creates a safety problem: contributions that are admissible in isolation can jointly enable a prohibited use. Blocking every sensitive action avoids disclosure but defeats the...