IDEAgent：用於研究想法生成的代理式品質多樣性搜尋

摘要

大型語言模型（LLMs）在過去幾年中已大幅自動化科學發現的過程。然而，現有系統皆有一個核心限制：它們在生成與優化想法時，要嘛獨立追求品質，要嘛獨立追求多樣性。這常導致產出的想法彼此高度相近，或產生大量瑣碎、不健全或含義不清的概念。在本研究中，我們主張研究構思應同時兼顧這兩個目標，並將其框架為品質-多樣性（QD）搜尋問題。基於此觀點，我們提出IDEAgent，一個透過世系（lineage）管理想法演化的多智能體框架。我們利用多目標回饋專門進行修復與精煉，共同驅動品質提升；同時，透過輕量級序列記憶體以及與已完成的構想、其歷史祖先及被拒絕提案的明確比較，來實現多樣性。為系統性評估此品質與多樣性的結合，我們開發了Yield這個聯合指標，用以計算在滿足預設品質門檻下，最大的相互多樣化構想集合。最後，透過橫跨電腦科學8個領域共32個主題的評估，我們顯示IDEAgent在Yield指標上超越最佳基線3.89倍，並且在8倍於基線的主題數量上達到非零的Yield。我們進一步透過品質改善分析佐證這些發現，顯示修復與精煉對於建立邏輯嚴謹性與清晰度、同時保持非顯而易見性至關重要。為鼓勵未來基於QD搜尋的構想研究，我們將IDEAgent開源於 https://github.com/declare-lab/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.