mlsanityData to 14 Oct 2026

AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Research

arXiv 2505.12039 ↗First posted 17 May 2025cs.AI cs.CL physics.soc-phcited by 3

Not on the map. Why?

Abstract (arXiv)

The Science of Science (SoS) explores the mechanisms underlying scientific discovery, and offers valuable insights for enhancing scientific efficiency and fostering innovation. Traditional approaches often rely on simplistic assumptions and basic statistical tools, such as linear regression and rule-based simulations, which struggle to capture the complexity and scale of modern research ecosystems. The advent of artificial intelligence (AI) presents a transformative opportunity for the next generation of SoS, enabling the automation of large-scale pattern discovery and uncovering insights previously unattainable. This paper offers a forward-looking perspective on the integration of Science of Science with AI for automated research pattern discovery and highlights key open challenges that could greatly benefit from AI. We outline the advantages of AI over traditional methods, discuss potential limitations, and propose pathways to overcome them. Additionally, we present a preliminary multi-agent system as an illustrative example to simulate research societies, showcasing AI's ability to replicate real-world research patterns and accelerate progress in Science of Science research.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 38 of its 108 references that are in the map. First posted on arXiv 17 May 2025.

Builds on

38 of 108 references.

References · 38

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2024Qwen2.5 Technical Reportcited by 4,942
  6. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  7. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  8. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  9. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
  10. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  11. 2019Passage Re-ranking with BERTcited by 645
  12. 2018Improving fairness in machine learning systems: What do industry practitioners need?cited by 262
26 more
  1. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 257
  2. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
  3. 2017Fairness in Machine Learning: Lessons from Political Philosophycited by 149
  4. 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 132
  5. 2021On Releasing Annotator-Level Labels and Information in Datasetscited by 126
  6. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 125
  7. 2024ChemLLM: A Chemical Large Language Modelcited by 106
  8. 2024SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoningcited by 94
  9. 2023Benchmarking Large Language Models on CMExam -- A Comprehensive Chinese Medical Exam Datasetcited by 91
  10. 2024Causal machine learning for predicting treatment outcomescited by 74
  11. 2024MoralBench: Moral Evaluation of LLMscited by 50
  12. 2024Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challengescited by 41
  13. 2015AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discoverycited by 38
  14. 2024Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluationcited by 34
  15. 2024Multi-Agent Collaboration via Cross-Team Orchestrationcited by 30
  16. 2019Predicting Research Trends with Semantic and Neural Networks with an application in Quantum Physicscited by 25
  17. 2022Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Modelcited by 25
  18. 2019The Diversity-Innovation Paradox in Sciencecited by 21
  19. 2019Early-career setback and future career impactcited by 8
  20. 2023Materials Discovery with Extreme Properties via Reinforcement Learning-Guided Combinatorial Chemistrycited by 5
  21. 2015Which type of citation analysis generates the most accurate taxonomy of scientific and technical knowledge?cited by 4
  22. 2017Citation-based clustering of publications using CitNetExplorer and VOSviewercited by 4
  23. 2019Quantifying dynamics of failure across science, startups, and securitycited by 4
  24. 2019Achieving competitive advantage in academia through early career coauthorship with top scientistscited by 3
  25. 2017Network dynamics of innovation processescited by 2
  26. 2017The Evolutions of the Rich get Richer and the Fit get Richer Phenomena in Scholarly Networks: The Case of the Strategic Management Journalcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Frameworkcited by 2
  2. 2026An Investigation of the NeurIPS and ICML 2025 Position Trackscited by 0
  3. 2026When Vision Meets Graphs: A Survey on Graph Reasoning and Learningcited by 0