CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving

TL;DR

This paper introduces CoMM, a multi-agent prompting framework where role-playing LLMs collaboratively solve complex science problems, significantly improving reasoning capabilities over traditional methods.

Contribution

The paper proposes a novel multi-agent, multi-reasoning-path prompting approach that enhances LLMs' problem-solving abilities through role differentiation and collaborative reasoning.

Findings

Effective on college-level science problems

Role-specific prompting improves reasoning performance

Collaborative multi-agent approach outperforms baselines

Abstract

Large Language Models (LLMs) have shown great ability in solving traditional natural language tasks and elementary reasoning tasks with appropriate prompting techniques. However, their ability is still limited in solving complicated science problems. In this work, we aim to push the upper bound of the reasoning capability of LLMs by proposing a collaborative multi-agent, multi-reasoning-path (CoMM) prompting framework. Specifically, we prompt LLMs to play different roles in a problem-solving team, and encourage different role-play agents to collaboratively solve the target task. In particular, we discover that applying different reasoning paths for different roles is an effective strategy to implement few-shot prompting approaches in the multi-agent scenarios. Empirical results demonstrate the effectiveness of the proposed methods on two college-level science problems over competitive baselines. Our further analysis shows the necessity of prompting LLMs to play different roles or experts independently. We release the code at: https://github.com/amazon-science/comm-prompt