SOURCE-LINKED INTELLIGENCE

Identity Is More Than Recall: A Benchmark for Persistent Identity in Deployed AI Agents

arXiv · AI, language, vision and robotics · article · Sep 12, 2026 · UTC

Persistent agents need evaluations that distinguish identity facts they can recall from those they express and enact. We introduce PAI-Bench, a provider-neutral benchmark for fidelity to a versioned, update-governed identity contract. It separates recall, composition, behavioral enactment, resistance, persistence, lineage, and role-conditioned updates while keeping scoring oracles outside the target process. Two frozen campaigns cover sixteen synthetic profiles, thirty-two probes, and three independently initialized target configurations, yielding 1,536 retained responses. A judge-independent

Read original source ↗ Open in workspace

recordType

paper

region

Global