An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhao, Xiutian, Wang, Ke, Peng, Wei
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914980659462144
author Zhao, Xiutian
Wang, Ke
Peng, Wei
author_facet Zhao, Xiutian
Wang, Ke
Peng, Wei
contents Modern large language models (LLMs) have exhibited cooperative synergy on complex task-solving, and collective decision-making (CDM) is a pivotal component in LLM-based multi-agent collaboration frameworks. Our survey on 52 recent such systems uncovers a severe lack of diversity, with a heavy reliance on dictatorial and plurality voting for CDM. Through the lens of social choice theory, we scrutinize widely-adopted CDM methods and identify their limitations. To enrich current landscape of LLM-based CDM, we present GEDI, an electoral CDM module that incorporates various ordinal preferential voting mechanisms. Our empirical case study across three benchmarks shows that the integration of certain CDM methods can markedly improve the reasoning capabilities and robustness of some leading LLMs, all without requiring intricate system designs. Additionally, we find that some CDM mechanisms generate positive synergies even with as few as three agents. The voting-based methods also demonstrate robustness against single points of failure, as well as diversity in terms of hit-rate@k and subject-wise impacts.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15168
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making
Zhao, Xiutian
Wang, Ke
Peng, Wei
Computation and Language
Modern large language models (LLMs) have exhibited cooperative synergy on complex task-solving, and collective decision-making (CDM) is a pivotal component in LLM-based multi-agent collaboration frameworks. Our survey on 52 recent such systems uncovers a severe lack of diversity, with a heavy reliance on dictatorial and plurality voting for CDM. Through the lens of social choice theory, we scrutinize widely-adopted CDM methods and identify their limitations. To enrich current landscape of LLM-based CDM, we present GEDI, an electoral CDM module that incorporates various ordinal preferential voting mechanisms. Our empirical case study across three benchmarks shows that the integration of certain CDM methods can markedly improve the reasoning capabilities and robustness of some leading LLMs, all without requiring intricate system designs. Additionally, we find that some CDM mechanisms generate positive synergies even with as few as three agents. The voting-based methods also demonstrate robustness against single points of failure, as well as diversity in terms of hit-rate@k and subject-wise impacts.
title An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making
topic Computation and Language
url https://arxiv.org/abs/2410.15168