Exploring Design of Multi-Agent LLM Dialogues for Research Ideation
This work provides practical guidelines for building multi-agent LLM systems to enhance scientific ideation, though it is incremental as it builds on existing structured dialogue approaches.
The study tackled the problem of optimizing multi-agent LLM dialogues for research idea generation by analyzing configurations like agent roles, number, and dialogue depth, finding that larger cohorts, deeper interactions, and increased critic diversity improved idea diversity and feasibility.
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.