Search papers, labs, and topics across Lattice.
This paper introduces IDEAgent, a multi-agent framework that integrates Quality and Diversity in research idea generation, addressing the limitations of existing systems that optimize for only one of these objectives. By employing a Quality-Diversity (QD) search approach, IDEAgent manages the evolution of ideas through lineages, utilizing multi-objective feedback for refinement and lightweight memory for diversity. Evaluations across 32 topics reveal that IDEAgent significantly outperforms existing baselines, achieving a 3.89x improvement in the Yield metric while enhancing the logical rigor and clarity of generated ideas.
IDEAgent achieves a staggering 3.89x improvement in generating diverse and high-quality research ideas compared to existing methods.
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.
