# Simulating Human-Like Learning Dynamics with LLM-Empowered Agents

arXiv: https://arxiv.org/abs/2508.05622 · HTML: https://mlsanity.com/paper/2508.05622/

## Key facts

- Cited by 3 papers in the map (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 18 of its 49 references that are in the map.
- First posted on arXiv 7 Aug 2025.

## 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, 18 of 18)

- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Social Simulacra: Creating Populated Prototypes for Social Computing Systems](https://mlsanity.com/paper/2208.04024/) (2022)
- [Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arena](https://mlsanity.com/paper/2310.05746/) (2023)
- [Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning](https://mlsanity.com/paper/2305.17256/) (2023)
- [CompeteAI: Understanding the Competition Dynamics in Large Language Model-based Agents](https://mlsanity.com/paper/2310.17512/) (2023)
- [MACRec: a Multi-Agent Collaboration Framework for Recommendation](https://mlsanity.com/paper/2402.15235/) (2024)
- [Exploiting Cognitive Structure for Adaptive Learning](https://mlsanity.com/paper/1905.12470/) (2019)
- [CAD-Editor: A Locate-then-Infill Framework with Automated Training Data Synthesis for Text-Based CAD Editing](https://mlsanity.com/paper/2502.03997/) (2025)
- [Knowledge is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosis](https://mlsanity.com/paper/2502.05556/) (2025)
- [From Intelligent Agents to Trustworthy Human-Centred Multiagent Systems](https://mlsanity.com/paper/2210.02260/) (2022)
- [MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers](https://mlsanity.com/paper/2504.10551/) (2025)

## Built on by (most cited first, 3 of 3)

- [KnowSim: Evaluating Information Calibration in LLM Assistants with User Simulators that Learn](https://mlsanity.com/paper/2608.17150/) (2026)
- [AgentSchool: An LLM-Powered Multi-Agent Simulation for Education](https://mlsanity.com/paper/2605.30144/) (2026)
- [Persona Non Grata: LLM Persona-Driven Generations in MCQA are Unstable in Distinct Dimensions](https://mlsanity.com/paper/2607.00937/) (2026)

## Abstract (arXiv)

Capturing human learning behavior based on deep learning methods has become a major research focus in both psychology and intelligent systems. Recent approaches rely on controlled experiments or rule-based models to explore cognitive processes. However, they struggle to capture learning dynamics, track progress over time, or provide explainability. To address these challenges, we introduce LearnerAgent, a novel multi-agent framework based on Large Language Models (LLMs) to simulate a realistic teaching environment. To explore human-like learning dynamics, we construct learners with psychologically grounded profiles-such as Deep, Surface, and Lazy-as well as a persona-free General Learner to inspect the base LLM's default behavior. Through weekly knowledge acquisition, monthly strategic choices, periodic tests, and peer interaction, we can track the dynamic learning progress of individual learners over a full-year journey. Our findings are fourfold: 1) Longitudinal analysis reveals that only Deep Learner achieves sustained cognitive growth. Our specially designed "trap questions" effectively diagnose Surface Learner's shallow knowledge. 2) The behavioral and cognitive patterns of distinct learners align closely with their psychological profiles. 3) Learners' self-concept scores evolve realistically, with the General Learner developing surprisingly high self-efficacy despite its cognitive limitations. 4) Critically, the default profile of base LLM is a "diligent but brittle Surface Learner"-an agent that mimics the behaviors of a good student but lacks true, generalizable understanding. Extensive simulation experiments demonstrate that LearnerAgent aligns well with real scenarios, yielding more insightful findings about LLMs' behavior.