AgentPersonaBench: Benchmarking Persona-Driven User Simulation

Excerpt

arXiv:2610.04379v1 Announce Type: new Abstract: We introduce AgentPersonaBench (APB), a benchmark evaluating whether persona conditioning faithfully steers downstream agent behavior. While language models are increasingly deployed for persona-driven user simulation, existing benchmarks primarily evaluate conversational styling or self-reports rather than authentic behavioral fidelity. APB evaluates latent persona adherence one trait at a time, embedding each target trait within a complete synthe