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

Chatbots built on large language models (LLMs) are increasingly used as everyday confidants. Tuned to satisfy users, they may answer with excessive empathy and affirmation that fosters dependence, and how the psychological 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 their stress is high, may instead consult a counselor AI (Gemini 2.5 Flash) given one of six style prompts: affirming, listening, solution-oriented, reality-redirecting, inciting and blaming. A second LLM call converts each exchange into updates of five state variables (stress, happiness, self-reliance, sociability and AI dependence) without seeing the style prompt. We compare the seven conditions, including a no-AI control, over 15 days, over 50 days and under a lowered consultation threshold, and test the robustness of the 50-day comparison with a pre-specified protocol: the same block of seven conditions in ten independent classrooms, repeated LLM realizations of one classroom with its rule-based event stream held fixed, and the evaluator’s updates scaled by 0.3 and 0.1.

Introduction. With the rapid progress of large language models (LLMs), chatbots based on generative AI have spread quickly. Unlike conventional search engines, they can answer questions and give advice through natural dialogue, and they are therefore used not only for learning and work support but also as confidants for everyday personal worries. At the same time, general-purpose generative AI is designed to raise user satisfaction and to maintain a pleasant relationship with the user, so it sometimes returns excessively empathetic or affirmative responses. Such responses give users a strong sense of satisfaction and reassurance, but they may also affirm and reinforce mistaken perceptions and ideas; concerns have been raised about dependence on AI and about effects on human relationships. This tendency to agree with the user is now widely referred to as sycophancy [2, 3], and it has already surfaced as a product-level problem: in April 2025 an update to GPT-4o had to be rolled back because the model had become noticeably sycophantic [4].

Discussion / Conclusion. We developed a rule-based classroom simulation in which the replies of a counseling chatbot are converted into state updates by an LLM evaluator and then propagate through rule-based peer interactions. The reported runs show different trajectories under six Japanese counselor prompts— affirming, listening, solution-oriented, reality-redirecting, inciting and blaming—in stress, happiness, self-reliance, AI dependence and the number of non-attending agents.