Identity Is More Than Recall: A Benchmark for Persistent Identity in Deployed AI Agents
arXiv:2609.13637v1 Announce Type: new Abstract: 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...
Read more: https://arxiv.org/abs/2609.13637
Scan with your phone
Scan with your phone