GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Tongxuan, Wang, Xingyu, Huang, Weizhe, Xu, Wenjiang, Zeng, Yuting, Jiang, Lei, Yang, Hailong, Li, Jing
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917169827151872
author Liu, Tongxuan
Wang, Xingyu
Huang, Weizhe
Xu, Wenjiang
Zeng, Yuting
Jiang, Lei
Yang, Hailong
Li, Jing
author_facet Liu, Tongxuan
Wang, Xingyu
Huang, Weizhe
Xu, Wenjiang
Zeng, Yuting
Jiang, Lei
Yang, Hailong
Li, Jing
contents In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse NLP tasks. Extensive research has explored how to enhance the logical reasoning abilities such as Chain-of-Thought, Chain-of-Thought with Self-Consistency, Tree-Of-Thoughts, and multi-agent debates. In the context of multi-agent debates, significant performance improvements can be achieved with an increasing number of agents and debate rounds. However, the escalation in the number of agents and debate rounds can drastically raise the tokens cost of debates, thereby limiting the scalability of the multi-agent debate technique. To better harness the advantages of multi-agent debates in logical reasoning tasks, this paper proposes a method to significantly reduce token cost in multi-agent debates. This approach involves dividing all agents into multiple debate groups, with agents engaging in debates within their respective groups and sharing interim debate results between groups. Comparative experiments across multiple datasets have demonstrated that this method can reduce the total tokens by up to 51.7% during debates and while potentially enhancing accuracy by as much as 25%. Our method significantly enhances the performance and efficiency of interactions in the multi-agent debate.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14051
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion
Liu, Tongxuan
Wang, Xingyu
Huang, Weizhe
Xu, Wenjiang
Zeng, Yuting
Jiang, Lei
Yang, Hailong
Li, Jing
Computation and Language
Artificial Intelligence
In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse NLP tasks. Extensive research has explored how to enhance the logical reasoning abilities such as Chain-of-Thought, Chain-of-Thought with Self-Consistency, Tree-Of-Thoughts, and multi-agent debates. In the context of multi-agent debates, significant performance improvements can be achieved with an increasing number of agents and debate rounds. However, the escalation in the number of agents and debate rounds can drastically raise the tokens cost of debates, thereby limiting the scalability of the multi-agent debate technique. To better harness the advantages of multi-agent debates in logical reasoning tasks, this paper proposes a method to significantly reduce token cost in multi-agent debates. This approach involves dividing all agents into multiple debate groups, with agents engaging in debates within their respective groups and sharing interim debate results between groups. Comparative experiments across multiple datasets have demonstrated that this method can reduce the total tokens by up to 51.7% during debates and while potentially enhancing accuracy by as much as 25%. Our method significantly enhances the performance and efficiency of interactions in the multi-agent debate.
title GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2409.14051