# AgentSchool: An LLM-Powered Multi-Agent Simulation for Education

arXiv: https://arxiv.org/abs/2605.30144 · HTML: https://mlsanity.com/paper/2605.30144/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 75 references that are in the map.
- First posted on arXiv 28 May 2026.

## Placed in

- LLM agents and tool use / [Educational agents and math problem solving](https://mlsanity.com/agents/educational-agents-and-math-problem-solving/)

## Builds on (most cited first, 11 of 11)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society](https://mlsanity.com/paper/2502.08691/) (2025)
- [Simulating Classroom Education with LLM-Empowered Agents](https://mlsanity.com/paper/2406.19226/) (2024)
- [Classroom Simulacra: Building Contextual Student Generative Agents in Online Education for Learning Behavioral Simulation](https://mlsanity.com/paper/2502.02780/) (2025)
- [MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework](https://mlsanity.com/paper/2504.21582/) (2025)
- [TutorUp: What If Your Students Were Simulated? Training Tutors to Address Engagement Challenges in Online Learning](https://mlsanity.com/paper/2502.16178/) (2025)
- [Modeling Earth-Scale Human-Like Societies with One Billion Agents](https://mlsanity.com/paper/2506.12078/) (2025)
- [Sense and Sensitivity: Evaluating the simulation of social dynamics via Large Language Models](https://mlsanity.com/paper/2412.05093/) (2024)
- [Simulating Human-Like Learning Dynamics with LLM-Empowered Agents](https://mlsanity.com/paper/2508.05622/) (2025)
- [Evolutionary Reinforcement Learning based AI tutor for Socratic Interdisciplinary Instruction](https://mlsanity.com/paper/2512.11930/) (2025)
- [Data Science in an Agent-Based Simulation World](https://mlsanity.com/paper/2306.01764/) (2023)

## Abstract (arXiv)

Despite the rapid deployment of LLMs into classrooms, validating educational AI remains uniquely intractable: interventions act on developing learners whose cognitive and social trajectories are irreversibly shaped, while real-world trials are slow, ethically constrained, and institutionally locked. LLM-based educational simulators have emerged as a potential remedy, but many still collapse learning into persona-conditioned role-play and, when optimized only to reproduce existing classrooms, can structurally penalize the institutional novelty that pedagogical reform requires. In this work, we introduce AgentSchool, an LLM-driven multi-agent simulator that models learning as state transition rather than prompted behavior. AgentSchool couples cognitively growable student agents -- equipped with weighted subject knowledge graphs, thinking-workflow pools, and explicit misconceptions -- with adaptive teacher agents that plan, scaffold, and reflect along the Zone of Proximal Development, embedded in a configurable scenery generator that situates instruction within both formal and informal learning fields, and a multi-scale simulator that decouples interaction scale, temporal granularity, and simulation duration. Experiments show that structured student agents produce more differentiated mastery and misconception traces than a baseline simulator, while teacher-agent comparisons show backbone-dependent patterns consistent with ZPD-informed adaptation. Further, AgentSchool generates plausible traces of peripheral participation, clique formation, aggressor-induced cohesion, and opinion-leader emergence consistent with classroom social theories. Beyond its role as an educational research instrument, AgentSchool frames education as a socially meaningful testbed for long-horizon memory, multi-agent coordination, and future institutional reasoning under organizational pressure.