Exploring Communication Strategies for Collaborative LLM Agents in Mathematical Problem-Solving

Liang Zhang, Xiaoming Zhai, Jionghao Lin, Jionghao Lin, Jennifer Kleiman +5 more
5/2/2025
cs.HCcs.AIcs.CL

No official code found. Best implementation: LiangZhang2017/aied_dual_agent (1 star, last commit 2025-03-27).

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.

View on arXivView PDF

Code Implementations(1)

LiangZhang2017/aied_dual_agentCommunity66%

This is for Exploring Communication Strategies for Collaborative LLM Agents in Mathematical Problem-Solving

10PythonFeb 20, 20251 years ago

Similar Papers

MathLearner: A Large Language Model Agent Framework for Learning to Solve Mathematical Problems

83% match2024

EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue Framework

83% match2025

Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry

83% match1 repo32025

CoLa: Learning to Interactively Collaborate with Large Language Models

83% match2025

Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents

82% match2023

Assessing the Creativity of LLMs in Proposing Novel Solutions to Mathematical Problems

82% match1 repo132024

Cite this paper

@article{zhang2025exploring,
  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},
  year   = {2025},
  eprint = {2507.17753},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.17753v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2507.17753.svg)](https://codeofpaper.com/paper/2507.17753)

Discussion