Exploring Design of Multi-Agent LLM Dialogues for Research Ideation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ueda, Keisuke, Hirota, Wataru, Asakura, Takuto, Omi, Takahiro, Takahashi, Kosuke, Arima, Kosuke, Ishigaki, Tatsuya
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909684241268736
author Ueda, Keisuke
Hirota, Wataru
Asakura, Takuto
Omi, Takahiro
Takahashi, Kosuke
Arima, Kosuke
Ishigaki, Tatsuya
author_facet Ueda, Keisuke
Hirota, Wataru
Asakura, Takuto
Omi, Takahiro
Takahashi, Kosuke
Arima, Kosuke
Ishigaki, Tatsuya
contents Large language models (LLMs) are increasingly used to support creative tasks such as research idea generation. While recent work has shown that structured dialogues between LLMs can improve the novelty and feasibility of generated ideas, the optimal design of such interactions remains unclear. In this study, we conduct a comprehensive analysis of multi-agent LLM dialogues for scientific ideation. We compare different configurations of agent roles, number of agents, and dialogue depth to understand how these factors influence the novelty and feasibility of generated ideas. Our experimental setup includes settings where one agent generates ideas and another critiques them, enabling iterative improvement. Our results show that enlarging the agent cohort, deepening the interaction depth, and broadening agent persona heterogeneity each enrich the diversity of generated ideas. Moreover, specifically increasing critic-side diversity within the ideation-critique-revision loop further boosts the feasibility of the final proposals. Our findings offer practical guidelines for building effective multi-agent LLM systems for scientific ideation. Our code is available at https://github.com/g6000/MultiAgent-Research-Ideator.
format Preprint
id arxiv_https___arxiv_org_abs_2507_08350
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Design of Multi-Agent LLM Dialogues for Research Ideation
Ueda, Keisuke
Hirota, Wataru
Asakura, Takuto
Omi, Takahiro
Takahashi, Kosuke
Arima, Kosuke
Ishigaki, Tatsuya
Computation and Language
Multiagent Systems
I.2.11; I.2.7
Large language models (LLMs) are increasingly used to support creative tasks such as research idea generation. While recent work has shown that structured dialogues between LLMs can improve the novelty and feasibility of generated ideas, the optimal design of such interactions remains unclear. In this study, we conduct a comprehensive analysis of multi-agent LLM dialogues for scientific ideation. We compare different configurations of agent roles, number of agents, and dialogue depth to understand how these factors influence the novelty and feasibility of generated ideas. Our experimental setup includes settings where one agent generates ideas and another critiques them, enabling iterative improvement. Our results show that enlarging the agent cohort, deepening the interaction depth, and broadening agent persona heterogeneity each enrich the diversity of generated ideas. Moreover, specifically increasing critic-side diversity within the ideation-critique-revision loop further boosts the feasibility of the final proposals. Our findings offer practical guidelines for building effective multi-agent LLM systems for scientific ideation. Our code is available at https://github.com/g6000/MultiAgent-Research-Ideator.
title Exploring Design of Multi-Agent LLM Dialogues for Research Ideation
topic Computation and Language
Multiagent Systems
I.2.11; I.2.7
url https://arxiv.org/abs/2507.08350