IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation

Hugging Face Daily Papers Papers
llm multi-agent scientific-discovery quality-diversity research-ideation open-source

Summary

IDEAgent introduces a multi-agent framework that treats research ideation as a Quality-Diversity search, jointly optimizing idea quality and diversity through lineage evolution, outperforming baselines by 3.89x on a novel joint metric.

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.
Original Article
View Cached Full Text

Cached at: 07/27/26, 05:39 AM

Paper page - IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation

Source: https://huggingface.co/papers/2607.22375

Abstract

LargeLanguageModels(LLMs)havesignificantlyautomatedtheprocessofscientificdiscoveryoverthepastfewyears.However,existingsystemsshareonecorelimitation:theygenerateandoptimizeideasindependentlyforeitherQualityorDiversity.Thisoftenleadstothegenerationofideasincloseproximitytooneanotherortoalargesetoftrivial,unsound,orunclearconcepts.Inthiswork,weinsteadarguethatresearchideationshouldbetreatedasaconjunctionofbothobjectivesandframedasaQuality-Diversity(QD)search.Inlinewiththisperspective,weintroduceIDEAgent,amulti-agentframeworkthatmanagestheevolutionofideasthroughlineages.WejointlydriveQualityusingmulti-objectivefeedbackfordedicatedrepairandrefinement,whileDiversityisachievedthroughlightweightsequentialmemoryandexplicitcomparisonagainstcompletedideas,theirhistoricalancestors,andrejectedproposals.TosystematicallyevaluatethisQDconjunction,wedevelopYield,ajointmetricthatcomputesthelargestsetofmutuallydiverseideasthatsatisfyapredeterminedqualitythreshold.Finally,throughevaluationsacross32topicsspanning8domainsofComputerScience,weshowthatIDEAgentoutperformsthebestbaselineby3.89xonYield,whileachievingnon-zeroYieldon8xmoretopics.Wefurthercorroboratethesefindingsthroughananalysisofqualityimprovements,showingthatrepairandrefinementarecrucialforbuildinglogicalrigorandclaritywhilepreservingnon-obviousness.ToencouragefutureresearchonQD-search-basedideation,weopen-sourceIDEAgentathttps://github.com/declare-lab/IDEAgent.

View arXiv pageView PDFGitHub1Add to collection

Get this paper in your agent:

hf papers read 2607\.22375

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.22375 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.22375 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.22375 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

SwarmResearch: Orchestrating Coding Agents for Open-Ended Discovery

arXiv cs.AI

SwarmResearch introduces an orchestrator-subagent harness where a Shepherd Agent steers a population of Search Agents to explore diverse solutions for open-ended optimization problems, achieving better or comparable results to state-of-the-art methods on 13/15 tasks.

EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery

Papers with Code Trending

EvoScientist is an adaptive multi-agent framework for end-to-end scientific discovery that continuously improves through persistent memory modules, comprising three specialized agents for idea generation, experiment execution, and knowledge distillation. It outperforms 7 state-of-the-art systems in scientific idea generation and improves code execution success rates through multi-agent evolution.