A Multi-Agent Psychological Simulation System for Human Behavior Modeling

TL;DR

This paper tackles the challenge of generating authentic, context-sensitive human behavior in simulations for training and research. It introduces a multi-agent 'inner parliament' that models internal cognitive-affective processes, allowing behavior to emerge from deliberation among agents grounded in established psychological theories. The work provides a transparent, parameterizable agent library and an internal-deliberation mechanism that yields interpretable transcripts of decision-making, with applicability to teacher education, psychological theory testing, and broader professional skills training. The approach advances practical realism, aligns with learning theories such as social constructivism and cognitive apprenticeship, and offers a scalable platform for hypothesis testing and cognitive apprenticeship. The system thus supports improved training outcomes and deeper insights into the hidden dynamics of human thought and emotion.

Abstract

Training and education in human-centered fields require authentic practice, yet realistic simulations of human behavior have remained limited. We present a multi-agent psychological simulation system that models internal cognitive-affective processes to generate believable human behaviors. In contrast to black-box neural models, this system is grounded in established psychological theories (e.g., self-efficacy, mindset, social constructivism) and explicitly simulates an ``inner parliament'' of agents corresponding to key psychological factors. These agents deliberate and interact to determine the system's output behavior, enabling unprecedented transparency and alignment with human psychology. We describe the system's architecture and theoretical foundations, illustrate its use in teacher training and research, and discuss how it embodies principles of social learning, cognitive apprenticeship, deliberate practice, and meta-cognition.

Figures (2)

• Figure 1: A screenshot of the simulation interface during an algebra problem scenario. The teacher (user) has posed an algebra question, and the simulated student responds with hesitation and self-doubt, reflecting high Math-Anxiety and low Self-Efficacy in this context.
• Figure 2: The "Peek Into the Brain" view showing the internal deliberation among agents corresponding to the interaction in Figure \ref{['fig:interface']}. Each agent's utterances are shown (e.g., the Threat-Avoidance agent advocating avoidance, the Self-Efficacy agent providing little resistance). This transparent transcript illustrates which psychological factors led to the student's behavior.