IDEAgent: 基于智能体质量多样性搜索的研究思路生成方法

摘要

近年来，大型语言模型（LLMs）显著推动了科学发现过程的自动化。然而，现有系统存在一个核心局限：它们独立地针对"质量"或"多样性"生成和优化想法，这往往导致生成的构思彼此高度相近，或产生大量琐碎、不严谨或模糊的概念。本研究提出，研究构思应被视作两项目标的结合，并构建为"质量-多样性（QD）搜索"框架。基于这一视角，我们引入IDEAgent——一个通过谱系管理想法演化的多智能体框架。我们利用多目标反馈联合驱动"质量"，实现针对性的修复与优化；同时通过轻量级序列记忆与显式对比（对比已完成想法、历史祖先及被拒绝提案）实现"多样性"。为系统评估这种QD联合效应，我们开发了Yield指标——一种联合度量标准，用于计算满足预定质量阈值且彼此多样化的最大想法集合。最后，在横跨8个计算机科学领域的32个主题上的评估显示，IDEAgent在Yield指标上超越最佳基线3.89倍，并在8倍更多的主题上实现了非零Yield值。我们进一步通过质量改进分析佐证这些发现，表明修复与优化对于构建逻辑严谨性与清晰度（同时保留非显而易见性）至关重要。为鼓励基于QD搜索的构思研究，我们在https://github.com/declare-lab/IDEAgent开源了IDEAgent。

English

Large Language Models (LLMs) have significantly automated the process of scientific discovery over the past few years. However, existing systems share one core limitation: they generate and optimize ideas independently for either Quality or Diversity. This often leads to the generation of ideas in close proximity to one another or to a large set of trivial, unsound, or unclear concepts. In this work, we instead argue that research ideation should be treated as a conjunction of both objectives and framed as a Quality-Diversity (QD) search. In line with this perspective, we introduce IDEAgent, a multi-agent framework that manages the evolution of ideas through lineages. We jointly drive Quality using multi-objective feedback for dedicated repair and refinement, while Diversity is achieved through lightweight sequential memory and explicit comparison against completed ideas, their historical ancestors, and rejected proposals. To systematically evaluate this QD conjunction, we develop Yield, a joint metric that computes the largest set of mutually diverse ideas that satisfy a predetermined quality threshold. Finally, through evaluations across 32 topics spanning 8 domains of Computer Science, we show that IDEAgent outperforms the best baseline by 3.89x on Yield, while achieving non-zero Yield on 8x more topics. We further corroborate these findings through an analysis of quality improvements, showing that repair and refinement are crucial for building logical rigor and clarity while preserving non-obviousness. To encourage future research on QD-search-based ideation, we open-source IDEAgent at https://github.com/declare-lab/IDEAgent.