mlsanityData to 14 Oct 2026

Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas

arXiv 2410.14255 ↗First posted 18 Oct 2024cs.AI cs.CLcited by 57

Not on the map. Why?

Abstract (arXiv)

Scientific innovation is pivotal for humanity, and harnessing large language models (LLMs) to generate research ideas could transform discovery. However, existing LLMs often produce simplistic and repetitive suggestions due to their limited ability in acquiring external knowledge for innovation. To address this problem, we introduce an enhanced planning and search methodology designed to boost the creative potential of LLM-based systems. Our approach involves an iterative process to purposely plan the retrieval of external knowledge, progressively enriching the idea generation with broader and deeper insights. Validation through automated and human assessments indicates that our framework substantially elevates the quality of generated ideas, particularly in novelty and diversity. The number of unique novel ideas produced by our framework is 3.4 times higher than without it. Moreover, our method outperforms the current state-of-the-art, generating at least 2.5 times more top-rated ideas based on 170 seed papers in a Swiss Tournament evaluation.

Key facts. Cited by 57 papers in the map (data through 14 Oct 2026). Builds on 12 of its 23 references that are in the map. First posted on arXiv 18 Oct 2024.

Builds on

12 of 23 references.

References · 12

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  3. 2022Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentscited by 1,035
  4. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  5. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  6. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentationcited by 366
  7. 2024Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researcherscited by 363
  8. 2024Monte Carlo Tree Search Boosts Reasoning via Iterative Preference Learningcited by 241
  9. 2023SciMON: Scientific Inspiration Machines Optimized for Noveltycited by 179
  10. 2023SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoningcited by 159
  11. 2023Large Language Models for Automated Open-domain Scientific Hypotheses Discoverycited by 100
  12. 2024MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agentscited by 67

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 28; 2026: 26.

57 papers.

Sort:

By area:

  1. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  2. 2025DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Processcited by 100
  3. 2025From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoverycited by 93
  4. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 77
  5. 2025SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writingcited by 49
  6. 2025Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluationcited by 42
  7. 2024ResearchTown: Simulator of Human Research Communitycited by 37
  8. 2024Evaluating LLMs' Divergent Thinking Capabilities for Scientific Idea Generation with Minimal Contextcited by 28
  9. 2025Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedbackcited by 25
  10. 2025AI Scientists Fail Without Strong Implementation Capabilitycited by 21
  11. 2025IRIS: Interactive Research Ideation System for Accelerating Scientific Discoverycited by 19
  12. 2024AIGS: Generating Science from AI-Powered Automated Falsificationcited by 18
38 more
  1. 2025MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Searchcited by 15
  2. 2025How Far Are AI Scientists from Changing the World?cited by 15
  3. 2025GIScience in the Era of Artificial Intelligence: A Research Agenda Towards Autonomous GIScited by 14
  4. 2025CellForge: Agentic Design of Virtual Cell Modelscited by 13
  5. 2025A Survey of AI Scientistscited by 11
  6. 2026AI for Auto-Research: Roadmap & User Guidecited by 11
  7. 2026Measuring the Gap Between Human and LLM Research Ideascited by 10
  8. 2025Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Modelscited by 9
  9. 2026Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistancecited by 9
  10. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 9
  11. 2025From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systemscited by 8
  12. 2025GEAR: A General Evaluation Framework for Abductive Reasoningcited by 6
  13. 2026Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientistscited by 6
  14. 2025Scaling Laws in Scientific Discovery with AI and Robot Scientistscited by 5
  15. 2025Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Riskscited by 5
  16. 2025From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Modelscited by 5
  17. 2026ASI-Evolve: AI Accelerates AIcited by 5
  18. 2025Enabling AI Scientists to Recognize Innovation: A Domain-Agnostic Algorithm for Assessing Noveltycited by 4
  19. 2025FML-bench: Benchmarking Machine Learning Agents for Scientific Researchcited by 4
  20. 2025Idea2Plan: Exploring AI-Powered Research Planningcited by 4
  21. 2026SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Promptscited by 4
  22. 2026NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automationcited by 4
  23. 2025Bayes-Entropy Collaborative Driven Agents for Research Hypotheses Generation and Optimizationcited by 2
  24. 2026Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluationcited by 2
  25. 2026Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contextscited by 2
  26. 2026ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomescited by 2
  27. 2026LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generationcited by 2
  28. 2025Pastiche Novel Generation Creating: Fan Fiction You Love in Your Favorite Author's Stylecited by 1
  29. 2025FRAME: Feedback-Refined Agent Methodology for Enhancing Medical Research Insightscited by 1
  30. 2025DeepResearchEco: A Recursive Agentic Workflow for Complex Scientific Question Answering in Ecologycited by 1
  31. 2026Capability-Aware Early-Stage Research Idea Evaluationcited by 1
  32. 2026Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generationcited by 1
  33. 2026EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generationcited by 1
  34. 2026Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methodscited by 1
  35. 2026Tree-of-Ideas: Automated Research Ideation via Cross-Trajectory Reasoning over Scholarly Evolutioncited by 1
  36. 2025Inclusion Arena: An Open Platform for Evaluating Large Foundation Models with Real-World Appscited by 0
  37. 2026Grounding LLMs in Scientific Discovery via Embodied Actionscited by 0
  38. 2026MOOSE-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained Scientific Hypothesis Discoverycited by 0

50 most cited of 57 All 57 (JSON)