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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Liang, Zhai, Xiaoming, Lin, Jionghao, Kleiman, Jennifer, Zapata-Rivera, Diego, Forsyth, Carol, Jiang, Yang, Hu, Xiangen, Graesser, Arthur C.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916860635643904
author Zhang, Liang
Zhai, Xiaoming
Lin, Jionghao
Lin, Jionghao
Kleiman, Jennifer
Zapata-Rivera, Diego
Forsyth, Carol
Jiang, Yang
Hu, Xiangen
Graesser, Arthur C.
author_facet Zhang, Liang
Zhai, Xiaoming
Lin, Jionghao
Lin, Jionghao
Kleiman, Jennifer
Zapata-Rivera, Diego
Forsyth, Carol
Jiang, Yang
Hu, Xiangen
Graesser, Arthur C.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_17753
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Communication Strategies for Collaborative LLM Agents in Mathematical Problem-Solving
Zhang, Liang
Zhai, Xiaoming
Lin, Jionghao
Lin, Jionghao
Kleiman, Jennifer
Zapata-Rivera, Diego
Forsyth, Carol
Jiang, Yang
Hu, Xiangen
Graesser, Arthur C.
Human-Computer Interaction
Artificial Intelligence
Computation and Language
Computers and Society
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.
title Exploring Communication Strategies for Collaborative LLM Agents in Mathematical Problem-Solving
topic Human-Computer Interaction
Artificial Intelligence
Computation and Language
Computers and Society
url https://arxiv.org/abs/2507.17753