Exploring Communication Strategies for Collaborative LLM Agents in Mathematical Problem-Solving
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| 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 |