mlsanityData to 14 Oct 2026

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

arXiv 2507.17753 ↗First posted 2 May 2025cs.HC cs.AI cs.CLcited by 0

On the map: LLM agents and tool use → Educational agents and math problem solving

Abstract (arXiv)

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, textitteacher-student interaction, textitpeer-to-peer collaboration, textitreciprocal peer teaching, and textitcritical 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 textitpeer-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.

Key facts. No citing papers in the map yet (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 14 of its 23 references that are in the map. First posted on arXiv 2 May 2025.

Builds on

14 of 23 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024From MOOC to MAIC: Reshaping Online Teaching and Learning through LLM-driven Agents5 Sep

Other references · 13

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  3. 2024GPT-4o System Cardcited by 4,588
  4. 2023Theory of Mind for Multi-Agent Collaboration via Large Language Modelscited by 135
  5. 2023Applying Large Language Models and Chain-of-Thought for Automatic Scoringcited by 69
  6. 2024MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Educationcited by 37
  7. 2024MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactionscited by 26
  8. 2024A Systematic Assessment of OpenAI o1-Preview for Higher Order Thinking in Educationcited by 16
  9. 2024SPL: A Socratic Playground for Learning Powered by Large Language Modelcited by 9
  10. 2023Does Informativeness Matter? Active Learning for Educational Dialogue Act Classificationcited by 8
  11. 2024Predicting Learning Performance with Large Language Models: A Study in Adult Literacycited by 8
  12. 2023Robust Educational Dialogue Act Classifiers with Low-Resource and Imbalanced Datasetscited by 5
1 more
  1. 2024Data Augmentation for Sparse Multidimensional Learning Performance Data Using Generative AIcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023MathChat: Converse to Tackle Challenging Math Problems with LLM Agents
  2. 2026Enhancing LLM Problem Solving via Tutor-Student Multi-Agent Interaction
  3. 2025LLM Agents for Education: Advances and Applications
  4. 2025EducationQ: Evaluating LLMs' Teaching Capabilities Through Multi-Agent Dialogue Framework
  5. 2024Synergistic Simulations: Multi-Agent Problem Solving with Large Language Models
  6. 2025Enabling Multi-Agent Systems as Learning Designers: Applying Learning Sciences to AI Instructional Design
  7. 2025Multi-Agent Collaborative Framework For Math Problem Generation
  8. 2025Literature Review Of Multi-Agent Debate For Problem-Solving