How a Chatbot's Response Style Shapes a Classroom: A Multi-Agent Simulation of Students Consulting AI

תקציר מקורי באנגליתarXiv:2609.05018v2 Announce Type: replace-cross Abstract: LLM chatbots are increasingly used as everyday confidants; tuned to satisfy users, they can answer with excessive empathy and affirmation that may foster dependence. How the states and relationships of many users co-evolve when they keep consulting an AI is hard to observe in real settings. We build a virtual classroom in which 20 student agents interact through rule-based chats, quarrels and consultations with friends and, when stressed, may instead consult a counselor AI (Gemini 2.5 Flash) given one of six style prompts (affirming, listening, solution-oriented, reality-redirecting, inciting, blaming). A second LLM call converts each exchange into updates of five state variables (stress, happiness, self-reliance, sociability, AI de