Exploring Communication Strategies for Collaborative LLM Agents in Mathematical Problem-Solving
Abstract
Large Language Model (LLM) agents are increasingly utilized in AI-aided education to support tutoring and learning. Effective communication strategies among LLM agents improve collaborative problem-solving efficiency and facilitate cost-effective adoption in education. However, little research has systematically evaluated the impact of different communication strategies on agents' problem-solving. Our study examines four communication modes, \textit{teacher-student interaction}, \textit{peer-to-peer collaboration}, \textit{reciprocal peer teaching}, and \textit{critical debate}, in a dual-agent, chat-based mathematical problem-solving environment using the OpenAI GPT-4o model. Evaluated on the MATH dataset, our results show that dual-agent setups outperform single agents, with \textit{peer-to-peer collaboration} achieving the highest accuracy. Dialogue acts like statements, acknowledgment, and hints play a key role in collaborative problem-solving. While multi-agent frameworks enhance computational tasks, effective communication strategies are essential for tackling complex problems in AI education.
Cite
@article{arxiv.2507.17753,
title = {Exploring Communication Strategies for Collaborative LLM Agents in Mathematical Problem-Solving},
author = {Liang Zhang and Xiaoming Zhai and Jionghao Lin and Jionghao Lin and Jennifer Kleiman and Diego Zapata-Rivera and Carol Forsyth and Yang Jiang and Xiangen Hu and Arthur C. Graesser},
journal= {arXiv preprint arXiv:2507.17753},
year = {2025}
}