探索用于研究构想的Multi-Agent LLM对话设计
Exploring Design of Multi-Agent LLM Dialogues for Research Ideation
AI总结：
本研究全面分析了Multi-Agent LLM对话在科学构想中的设计，发现扩大agent群体、加深交互深度、拓宽角色异质性可丰富构想多样性，且在ideation-critique-revision循环中增加批评侧多样性能进一步提升最终提案的可行性。
摘要：
大型语言模型（LLMs）正越来越多地被用于支持创意任务，例如研究构想的生成。虽然最近的研究表明，LLMs之间的结构化对话可以提高生成构想的新颖性和可行性，但此类交互的最佳设计仍不明确。在本研究中，我们对用于科学构想的Multi-Agent LLM对话进行了全面分析。我们比较了agent角色、agent数量和对话深度的不同配置，以了解这些因素如何影响生成构想的新颖性和可行性。我们的实验设置包括一个agent生成构想而另一个agent对其进行批评的场景，从而实现迭代改进。我们的结果表明，扩大agent群体、加深交互深度以及拓宽agent角色异质性，均能丰富生成构想的多样性。此外，在ideation-critique-revision循环中，专门增加批评侧的多样性，可进一步提升最终提案的可行性。我们的发现为构建用于科学构想的有效Multi-Agent LLM系统提供了实用指南。我们的代码可在https://github.com/g6000/MultiAgent-Research-Ideator获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
