How a Chatbot's Response Style Shapes a Classroom: A Multi-Agent Simulation of Students Consulting AI
Rin Tamai and Yuya Dan at Matsuyama University simulate a classroom of 20 student agents who consult either a friend or a counselor AI when stressed, and vary the counselor's response style to see how AI dependence accumulates over days.
Ask this paper
Setup: Each agent carries five state variables (stress, happiness, self-reliance, AI dependence, sociability) across four daily phases. The counselor gets one of six system-prompt styles: affirming, listening, solution-oriented, reality-redirecting, inciting, blaming.
Blind evaluator: A second LLM call converts each consultation into parameter updates without seeing the style prompt, which keeps the style from directly writing its own outcome.
Results in simulation: The solution-oriented style kept AI dependence low while raising self-reliance and holding happiness. Affirming and inciting styles both raised AI dependence sharply, and inciting also raised stress and school non-attendance. The listening style did not relieve accumulated stress.
The authors' own caveat is the interesting part: They state these describe the simulated system, not measured human effects, give a full specification of the agent dynamics, and name the built-in mechanisms that produce the outcomes. Repeated runs, sensitivity analyses and human data are listed as prerequisites before any psychological claim.
Abstract
LLM-based chatbots are increasingly used as everyday confidants. Because they are designed to maximize user satisfaction, they can respond with excessive empathy and affirmation, which may reinforce mistaken beliefs and foster dependence on AI. While the psychological effects of chatbots on individual users have begun to be studied, how the psychological states and relationships of many users evolve when they keep consulting an AI is hard to observe in real settings. We build a virtual classroom simulation in which 20 student agents interact and, when stressed, consult either a friend or a counselor AI (Gemini 2.5 Flash). Each agent carries five state variables (stress, happiness, self-reliance, AI dependence, sociability), and each day has four phases (morning, noon, after school, night). The counselor is given six response styles via system prompts (affirming, listening, solution-oriented, reality-redirecting, inciting, blaming); a second LLM call acts as an evaluator that turns each consultation into parameter updates without seeing the style prompt. We compare the seven conditions, including a no-AI control, over 15 days in three classrooms, over 50 days, and under a lowered consultation threshold. In this simulation the solution-oriented style kept AI dependence low while raising self-reliance and maintaining happiness; the affirming and inciting styles markedly increased AI dependence, and the inciting style also increased stress and school non-attendance; the listening style did not relieve accumulated stress. The results describe the simulated system, not measured effects on humans. We give a complete specification of the agent dynamics, identify built-in mechanisms that shape the outcomes, and discuss the limitations of LLM-based evaluation and the validation steps (repeated runs, sensitivity analyses, human data) needed before psychological conclusions can be drawn.