AI RESEARCH
$\Psi$-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues
arXiv CS.LG
•
ArXi:2606.02754v1 Announce Type: new Personalization is a crucial capability of modern language agents. However, current research primarily positions personalized agents as passive responders to user preferences, limiting their ability to interact with users and provide suggestions or guidance proactively. To systematically evaluate such proactive personalization in realistic interactions, we propose $\Psi$-Bench, a benchmark for assessing LLMs' ability to influence realistic users through conversation.