Evolution in Simulation: AI-Agent School with Dual Memory for High-Fidelity Educational Dynamics

2025-10-13

AI Summary

Existing educational AI agents suffer from fragmented modeling and insufficient capability to simulate diverse stakeholders. To address this, we propose AI-Agent School—a unified framework for high-fidelity educational simulation. Methodologically, it introduces: (1) an experience–knowledge dual-memory architecture that decouples transient interaction traces from persistent pedagogical knowledge; (2) a Zero-Exp self-evolution strategy enabling agents to iteratively refine behavior via “experience–reflection–optimization” cycles without prior expertise; and (3) a context-aware interaction mechanism integrated with a long–short-term memory fusion framework to model authentic teacher–student dynamics and educational system dynamics. Experimental results demonstrate significant improvements in agent cognitive depth and scenario fidelity, advancing educational AI agents from static, experience-driven paradigms toward adaptive, evolvable simulation systems.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Machine Learning: Evolutionary Learning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Large language models (LLMs) based Agents are increasingly pivotal in simulating and understanding complex human systems and interactions. We propose the AI-Agent School (AAS) system, built around a self-evolving mechanism that leverages agents for simulating complex educational dynamics. Addressing the fragmented issues in teaching process modeling and the limitations of agents performance in simulating diverse educational participants, AAS constructs the Zero-Exp strategy, employs a continuous "experience-reflection-optimization" cycle, grounded in a dual memory base comprising experience and knowledge bases and incorporating short-term and long-term memory components. Through this mechanism, agents autonomously evolve via situated interactions within diverse simulated school scenarios. This evolution enables agents to more accurately model the nuanced, multi-faceted teacher-student engagements and underlying learning processes found in physical schools. Experiment confirms that AAS can effectively simulate intricate educational dynamics and is effective in fostering advanced agent cognitive abilities, providing a foundational stepping stone from the "Era of Experience" to the "Era of Simulation" by generating high-fidelity behavioral and interaction data.

Problem

• Simulating complex educational dynamics with AI agents
• Addressing fragmented teaching process modeling limitations
• Enhancing agent performance in modeling teacher-student interactions

Innovation

• Self-evolving AI agents with dual memory bases
• Zero-Exp strategy using experience-reflection-optimization cycle
• Simulating educational dynamics through autonomous agent evolution