# PeerGPT: Probing the Roles of LLM-based Peer Agents as Team Moderators and Participants in Children's Collaborative Learning

arXiv: https://arxiv.org/abs/2403.14227 · HTML: https://mlsanity.com/paper/2403.14227/

## Key facts

- Cited by 18 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 4 of its 35 references that are in the map.
- First posted on arXiv 21 Mar 2024.

## 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, 4 of 4)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Mathemyths: Leveraging Large Language Models to Teach Mathematical Language through Child-AI Co-Creative Storytelling](https://mlsanity.com/paper/2402.01927/) (2024)
- [UX Research on Conversational Human-AI Interaction: A Literature Review of the ACM Digital Library](https://mlsanity.com/paper/2202.09895/) (2022)
- [Curiosity Notebook: The Design of a Research Platform for Learning by Teaching](https://mlsanity.com/paper/2108.09809/) (2021)

## Built on by (most cited first, 18 of 18)

- [TeachTune: Reviewing Pedagogical Agents Against Diverse Student Profiles with Simulated Students](https://mlsanity.com/paper/2410.04078/) (2024)
- [EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue Framework](https://mlsanity.com/paper/2504.14928/) (2025)
- [A Survey on Human-Centric LLMs](https://mlsanity.com/paper/2411.14491/) (2024)
- [CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments](https://mlsanity.com/paper/2510.26852/) (2025)
- [Social Life Simulation for Non-Cognitive Skills Learning](https://mlsanity.com/paper/2405.00273/) (2024)
- [Carbon and Silicon, Coexist or Compete? A Survey on Human-AI Interactions in Agent-based Modeling and Simulation](https://mlsanity.com/paper/2502.18145/) (2025)
- [Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialogues](https://mlsanity.com/paper/2510.19028/) (2025)
- [Simulating Filter Bubble on Short-video Recommender System with Large Language Model Agents](https://mlsanity.com/paper/2504.08742/) (2025)
- [The Role of Generative AI in Facilitating Social Interactions: A Scoping Review](https://mlsanity.com/paper/2506.10927/) (2025)
- [Designing Smarter Conversational Agents for Kids: Lessons from Cognitive Work and Means-Ends Analyses](https://mlsanity.com/paper/2508.21209/) (2025)
- [LLMs and their Limited Theory of Mind: Evaluating Mental State Annotations in Situated Dialogue](https://mlsanity.com/paper/2509.02292/) (2025)
- [A Scoping Review of Large Language Model-Based Pedagogical Agents](https://mlsanity.com/paper/2604.12253/) (2026)
- [Learning Nonverbal Cues in Multiparty Social Interactions for Robotic Facilitators](https://mlsanity.com/paper/2501.10857/) (2025)
- [Diffusion-Based Imitation Learning for Social Pose Generation](https://mlsanity.com/paper/2501.10869/) (2025)
- [Exploring Learners' Expectations and Engagement When Collaborating with Constructively Controversial Peer Agents](https://mlsanity.com/paper/2601.13479/) (2026)
- [Dynamic Framework for Collaborative Learning: Leveraging Advanced LLM with Adaptive Feedback Mechanisms](https://mlsanity.com/paper/2601.21344/) (2026)
- [Exploring Teachers' Perspectives on Using Conversational AI Agents for Group Collaboration](https://mlsanity.com/paper/2602.07142/) (2026)
- [Exploring How Agent Voice Accents Shape Human-AI Collaboration in K-12 Group Learning](https://mlsanity.com/paper/2606.12805/) (2026)

## Abstract (arXiv)

In children's collaborative learning, effective peer conversations can significantly enhance the quality of children's collaborative interactions. The integration of Large Language Model (LLM) agents into this setting explores their novel role as peers, assessing impacts as team moderators and participants. We invited two groups of participants to engage in a collaborative learning workshop, where they discussed and proposed conceptual solutions to a design problem. The peer conversation transcripts were analyzed using thematic analysis. We discovered that peer agents, while managing discussions effectively as team moderators, sometimes have their instructions disregarded. As participants, they foster children's creative thinking but may not consistently provide timely feedback. These findings highlight potential design improvements and considerations for peer agents in both roles.