mlsanityData to 7 Oct 2026

IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback

arXiv 2410.04025 ↗First posted 5 Oct 2024cs.HC cs.AIcited by 40

Not on the map. Why?

Abstract (arXiv)

Research ideation involves broad exploring and deep refining ideas. Both require deep engagement with literature. Existing tools focus primarily on idea broad generation, yet offer little support for iterative specification, refinement, and evaluation needed to further develop initial ideas. To bridge this gap, we introduce IdeaSynth, a research idea development system that uses LLMs to provide literature-grounded feedback for articulating research problems, solutions, evaluations, and contributions. IdeaSynth represents these idea facets as nodes on a canvas, and allow researchers to iteratively refine them by creating and exploring variations and composing them. Our lab study (N=20) showed that participants, while using IdeaSynth, explored more alternative ideas and expanded initial ideas with more details compared to a strong LLM-based baseline. Our deployment study (N=7) demonstrated that participants effectively used IdeaSynth for real-world research projects at various ideation stages from developing initial ideas to revising framings of mature manuscripts, highlighting the possibilities to adopt IdeaSynth in researcher's workflows.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 27 of its 59 references that are in the map. First posted on arXiv 5 Oct 2024.

Builds on

27 of 59 references.

References · 27

  1. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  2. 2020SPECTER: Document-level Representation Learning using Citation-informed Transformerscited by 426
  3. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 348
  4. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 294
  5. 2023Can large language models provide useful feedback on research papers? A large-scale empirical analysiscited by 195
  6. 2023SciMON: Scientific Inspiration Machines Optimized for Noveltycited by 174
  7. 2024Homogenization Effects of Large Language Models on Human Creative Ideationcited by 127
  8. 2021To Trust or to Think: Cognitive Forcing Functions Can Reduce Overreliance on AI in AI-assisted Decision-makingcited by 118
  9. 2022Explanations Can Reduce Overreliance on AI Systems During Decision-Makingcited by 111
  10. 2023Large Language Models for Automated Open-domain Scientific Hypotheses Discoverycited by 100
  11. 2024Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Eracited by 97
  12. 2023Large Language Models are Zero Shot Hypothesis Proposerscited by 45
15 more
  1. 2024AI-Augmented Brainwriting: Investigating the use of LLMs in group ideationcited by 43
  2. 2024Human Creativity in the Age of LLMs: Randomized Experiments on Divergent and Convergent Thinkingcited by 43
  3. 2024Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluationcited by 39
  4. 2019PaperRobot: Incremental Draft Generation of Scientific Ideascited by 37
  5. 2024The Effects of Generative AI on Design Fixation and Divergent Thinkingcited by 37
  6. 2023CoQuest: Exploring Research Question Co-Creation with an LLM-based Agentcited by 34
  7. 2024Automated Focused Feedback Generation for Scientific Writing Assistancecited by 33
  8. 2023ConvXAI: Delivering Heterogeneous AI Explanations via Conversations to Support Human-AI Scientific Writingcited by 31
  9. 2023Has the Machine Learning Review Process Become More Arbitrary as the Field Has Grown? The NeurIPS 2021 Consistency Experimentcited by 31
  10. 2023Synergi: A Mixed-Initiative System for Scholarly Synthesis and Sensemakingcited by 25
  11. 2022A Computational Inflection for Scientific Discoverycited by 22
  12. 2022Augmenting Scientific Creativity with an Analogical Search Enginecited by 22
  13. 2022Augmenting Scientific Creativity with Retrieval across Knowledge Domainscited by 7
  14. 2023Towards Autonomous Hypothesis Verification via Language Models with Minimal Guidancecited by 7
  15. 2024Acceleron: A Tool to Accelerate Research Ideationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 25; 2026: 13.

40 papers.

Sort:

By area:

  1. 2025Levels of Autonomy for AI Agentscited by 45
  2. 2025Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluationcited by 41
  3. 2024Cocoa: Co-Planning and Co-Execution with AI Agentscited by 38
  4. 2024Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Contextcited by 25
  5. 2025AI Scientists Fail Without Strong Implementation Capabilitycited by 20
  6. 2025IRIS: Interactive Research Ideation System for Accelerating Scientific Discoverycited by 16
  7. 2025CellForge: Agentic Design of Virtual Cell Modelscited by 11
  8. 2025MIR: Methodology Inspiration Retrieval for Scientific Research Problemscited by 10
  9. 2025HypER: Literature-grounded Hypothesis Generation and Distillation with Provenancecited by 10
  10. 2025ScholarEval: Research Idea Evaluation Grounded in Literaturecited by 10
  11. 2025From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systemscited by 8
  12. 2025ScholarMate: A Mixed-Initiative Tool for Qualitative Knowledge Work and Information Sensemakingcited by 7
28 more
  1. 2026Measuring the Gap Between Human and LLM Research Ideascited by 7
  2. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 6
  3. 2025Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept Networkcited by 5
  4. 2026Learning to Predict Future-Aligned Research Proposals with Language Modelscited by 5
  5. 2025ClearFairy: Capturing Creative Workflows through Decision Structuring, In-Situ Questioning, and Rationale Inferencecited by 4
  6. 2026Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspirationcited by 4
  7. 2025Attribution Gradients: Incrementally Unfolding Citations for Critical Examination of Attributed AI Answerscited by 3
  8. 2026Beyond Divergent Creativity: A Human-Based Evaluation of Creativity in Large Language Modelscited by 3
  9. 2025The Design Space of Recent AI-assisted Research Tools for Ideation, Sensemaking, and Scientific Creativitycited by 2
  10. 2025Scaffolding Recursive Divergence and Convergence in Story Ideationcited by 2
  11. 2025StoryEnsemble: Enabling Dynamic Exploration & Iteration in the Design Process with AI and Forward-Backward Propagationcited by 2
  12. 2025AgentExpt: Automating AI Experiment Design with LLM-based Resource Retrieval Agentcited by 2
  13. 2025MirrorMind: Empowering OmniScientist with the Expert Perspectives and Collective Knowledge of Human Scientistscited by 2
  14. 2026Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Userscited by 2
  15. 2026Enhancing Research Idea Generation through Combinatorial Innovation and Multi-Agent Iterative Search Strategiescited by 2
  16. 2025Towards Automated Scoping of AI for Social Good Projectscited by 1
  17. 2025DeepResearchEco: A Recursive Agentic Workflow for Complex Scientific Question Answering in Ecologycited by 1
  18. 2025HypoChainer: A Collaborative System Combining LLMs and Knowledge Graphs for Hypothesis-Driven Scientific Discoverycited by 1
  19. 2025TreeReader: A Hierarchical Academic Paper Reader Powered by Language Modelscited by 1
  20. 2025Bayes-Entropy Collaborative Driven Agents for Research Hypotheses Generation and Optimizationcited by 1
  21. 2026Capability-Aware Early-Stage Research Idea Evaluationcited by 1
  22. 2026Style Wins, Substance Loses: A Diagnosis of LLM-as-Judge in Idea Generationcited by 1
  23. 2025PolicyPad: Collaborative Prototyping of LLM Policiescited by 0
  24. 2025Evolving and Executing Research Plans via Double-Loop Multi-Agent Collaborationcited by 0
  25. 2026Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agentscited by 0
  26. 2026LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscapecited by 0
  27. 2026MOOSE-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained Scientific Hypothesis Discoverycited by 0
  28. 2026DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documentscited by 0