Large Language Model-Guided Scientific Discovery

Overview

The field studies how large language models can help turn scientific literature and data into hypotheses, mechanisms, algorithms, and new materials, making discovery more systematic and widening the range of ideas scientists can test. Common approaches combine literature retrieval or knowledge graphs with tool-using agents, symbolic regression, evolutionary search, Bayesian optimization, and feedback from simulations or experiments. Work spans research-idea generation, equation and mechanism discovery, experimental planning, and materials or molecular design, with evaluation ranging from scientific benchmarks and formal verification to closed-loop laboratory tests. A central challenge is ensuring that promising outputs are novel, physically or biologically grounded, reproducible, and generalizable: strong predictive fit or fluent explanations alone do not establish a valid discovery, so independent checks and human oversight remain important.

Latest papers

CardsList

312 papers44 papers in the last four weeks, down 8% on the four weeks before. 0.3% of all new papers.

  1. Structured AI ideation yields physical strategies for epithelial barrier repair

    Nov 17, 2026Geonho Nah, Johyun Park, Kyung-Ah Cho +14Scientific Hypothesis GenerationResearch Idea Generation

  2. Towards Agentic Scientific Discovery in Distributed Systems

    Nov 15, 2026Rashmita Soni, Abhirup Ghosh, Soumya BanerjeeLarge Language Model-Guided Scientific DiscoveryTool Selection for Language Model Agents

  3. Asking the right question is key to AI discovery in a chain of hypotheses

    Nov 15, 2026Hu CangAutonomous Scientific DiscoveryLarge Language Model-Guided Scientific Discovery

  4. NeoResearch: Literature- and Experience-Guided Autonomous Time Series Model Discovery

    Nov 13, 2026Ze Guo, Mingyue Cheng, Xiaoyu Tao +2Time Series ModelingLarge Language Model-Guided Scientific Discovery

  5. Gradient-Aware AI Agents for Autonomous Turbulence Model Discovery via Differentiable CFD

    Nov 11, 2026Yi Liu, Xiantao Fan, Mingqi Xu +1Turbulence ModelingComputational Fluid Dynamics

  6. Pyrite: Building and Benchmarking Protein-Ligand Pose Ranking Agents

    Nov 10, 2026Megha Srivastava, Michael H. Lim, Allison M. Keys +2Learning to RankMolecular Docking

  7. Discovering Structurally Plausible and Interpretable Cognitive Models with Large Language Models

    Nov 10, 2026Boyoung Kwon, Jiyoon Seo, Sang Ho LeeComputational Cognitive ModelingCognitive Modeling

  8. MOTIF: LLM-Defined Material Taxonomies for OOD Property Prediction via Invariant Feature Selection

    Nov 9, 2026Gwangseon Jang, Sieun Yun, Dong Ho Lee +4Materials Property PredictionOOD Generalization

  9. AOP-Smart-Finder: A High-Throughput Human-AI Hybrid Framework for AOP Discovery and Evidence Mapping from Large-Scale Literature

    Nov 8, 2026Qinjiang Niu, Lu YanLarge Language Model-Guided Scientific DiscoveryRelation Extraction

  10. El Agente Fármaco: A Scalable AI Scientist for Drug Discovery

    Nov 2, 2026Marcel Müller, Mohammad Ghazi Vakili, Yoshihiro Ogura +13Drug DiscoveryScientific Workflow Automation

  11. IdeaTaste: Do LLMs Share the Research Taste of Human Researchers?

    Nov 2, 2026Shanshan Zhong, Chen Xu, Jingjie Ning +3Research Idea GenerationLLM Evaluation

  12. PRIME: Predictive Routing of Interventions by Modeling Effects for Scientific Ideation

    Nov 2, 2026Fengxian Ji, Xie Yu, Zhexuan Cui +8Large Language Model-Guided Scientific DiscoveryLanguage Model Self-Improvement

  13. Discovering hierarchical governing equations for community-structured complex network dynamics with LLM agents

    Nov 2, 2026Jinlei Zhang, Zixuan Zhang, Hao Qiu +8Scientific DiscoveryDynamical Systems

  14. RecRSI: Mechanism-Guided Discovery of Recommendation Algorithms

    Nov 2, 2026Tingran Gan, Zhouziyue Lu, Dian Jin +7Recommender SystemsAutomated Algorithm Discovery

  15. TIGER: Learning from Researcher Taste to Generate Tailored Research Ideas

    Nov 1, 2026Shane Gu, Yufeng Lin, Dixi Yao +2Research Idea GenerationLarge Language Model-Guided Scientific Discovery

  16. Evidence-grounded large language models guide perovskite solar cell design and optimization

    Oct 31, 2026YanKai Chen, Zhi Wan, ZiHao Li +1Perovskite Solar CellsLarge Language Model-Guided Scientific Discovery

  17. Unsatz: Evaluating Scientific Discovery Without a Given Ansatz

    Oct 31, 2026Ethan Ji, Wei Wang, Yizhou SunScientific DiscoveryLarge Language Model-Guided Scientific Discovery

  18. Discovering Models for Experimental Quantum Systems with Agentic AI

    Oct 31, 2026Hannah C. Kleidermacher, Bennet Windt, Miguel Bello +2Quantum System IdentificationAI Agents for Scientific Discovery