mlsanityData to 7 Oct 2026

Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition

arXiv 2510.15280 ↗First posted 17 Oct 2025cs.LG cs.AI cs.DLcited by 6

Not on the map. Why?

Abstract (arXiv)

Foundation models (FMs), such as GPT-4 and AlphaFold, are reshaping the landscape of scientific research. Beyond accelerating tasks such as hypothesis generation, experimental design, and result interpretation, they prompt a more fundamental question: Are FMs merely enhancing existing scientific methodologies, or are they redefining the way science is conducted? In this paper, we argue that FMs are catalyzing a transition toward a new scientific paradigm. We introduce a three-stage framework to describe this evolution: (1) Meta-Scientific Integration, where FMs enhance workflows within traditional paradigms; (2) Hybrid Human-AI Co-Creation, where FMs become active collaborators in problem formulation, reasoning, and discovery; and (3) Autonomous Scientific Discovery, where FMs operate as independent agents capable of generating new scientific knowledge with minimal human intervention. Through this lens, we review current applications and emerging capabilities of FMs across existing scientific paradigms. We further identify risks and future directions for FM-enabled scientific discovery. This position paper aims to support the scientific community in understanding the transformative role of FMs and to foster reflection on the future of scientific discovery. Our project is available at https://github.com/usail-hkust/Awesome-Foundation-Models-for-Scientific-Discovery.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 53 of its 100 references that are in the map. First posted on arXiv 17 Oct 2025.

Builds on

53 of 100 references.

References · 53

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2024Qwen2.5 Technical Reportcited by 4,713
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  5. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  6. 2022Galactica: A Large Language Model for Sciencecited by 736
  7. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  8. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
  9. 2023Towards Expert-Level Medical Question Answering with Large Language Modelscited by 382
  10. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 379
  11. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchcited by 375
  12. 2023ClimaX: A foundation model for weather and climatecited by 325
38 more
  1. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  2. 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 261
  3. 2023PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solverscited by 205
  4. 2021Large-Scale Chemical Language Representations Capture Molecular Structure and Propertiescited by 203
  5. 2024Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapterscited by 199
  6. 2023Augmenting Language Models with Long-Term Memorycited by 186
  7. 2024CycleResearcher: Improving Automated Research via Automated Reviewcited by 142
  8. 2023DiffusionSat: A Generative Foundation Model for Satellite Imagerycited by 130
  9. 2024Language agents achieve superhuman synthesis of scientific knowledgecited by 121
  10. 2024LLM-SR: Scientific Equation Discovery via Programming with Large Language Modelscited by 117
  11. 2024DiffusionPDE: Generative PDE-Solving Under Partial Observationcited by 100
  12. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agentscited by 96
  13. 2024Latent Neural Operator for Solving Forward and Inverse PDE Problemscited by 76
  14. 2024Symbolic Regression with a Learned Concept Librarycited by 76
  15. 2024OpenELM: An Efficient Language Model Family with Open Training and Inference Frameworkcited by 74
  16. 2024ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Areacited by 68
  17. 2024Agent Planning with World Knowledge Modelcited by 66
  18. 2022Continual Learning with Foundation Models: An Empirical Study of Latent Replaycited by 61
  19. 2024Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEscited by 58
  20. 2022CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representationscited by 56
  21. 2024Lean Copilot: Large Language Models as Copilots for Theorem Proving in Leancited by 52
  22. 2024BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experimentscited by 49
  23. 2024A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?cited by 46
  24. 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
  25. 2024Towards a Foundation Model for Partial Differential Equations: Multi-Operator Learning and Extrapolationcited by 45
  26. 2024PROSE-FD: A Multimodal PDE Foundation Model for Learning Multiple Operators for Forecasting Fluid Dynamicscited by 33
  27. 2025MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problemcited by 24
  28. 2023Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventionscited by 19
  29. 2024Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learningcited by 19
  30. 2024Hallucination Detection in Foundation Models for Decision-Making: A Flexible Definition and Review of the State of the Artcited by 17
  31. 2025Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoningcited by 17
  32. 2025Bag of Tricks for Inference-time Computation of LLM Reasoningcited by 15
  33. 2023OptoGPT: A Foundation Model for Inverse Design in Optical Multilayer Thin Film Structurescited by 13
  34. 2025Parameter-Efficient Continual Fine-Tuning: A Surveycited by 11
  35. 2024VISION: A Modular AI Assistant for Natural Human-Instrument Interaction at Scientific User Facilitiescited by 10
  36. 2024Bayesian Experimental Design via Contrastive Diffusionscited by 9
  37. 2024Relational Programming with Foundation Modelscited by 7
  38. 2025ScIRGen: Synthesize Realistic and Large-Scale RAG Dataset for Scientific Researchcited by 7

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026ST4VLA: Spatially Guided Training for Vision-Language-Action Modelscited by 8
  2. 2026Talk Freely, Execute Strictly: Schema-Gated Agentic AI for Flexible and Reproducible Scientific Workflowscited by 1
  3. 2026Workflow Closure Is Not Scientific Closure in Auto-Research Systemscited by 1
  4. 2026Towards a new paradigm of scientific discovery with socialized artificial intelligencecited by 0
  5. 2026Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systemscited by 0
  6. 2026An Investigation of the NeurIPS and ICML 2025 Position Trackscited by 0