Scientific Discovery

Ask about this topic

Overview

Scientific discovery studies how to turn observations and prior knowledge into new, testable explanations or useful candidates, from physical laws and biological mechanisms to materials and research questions. Common approaches include symbolic regression and causal or mechanistic modeling, machine-learning analysis, Bayesian optimization for choosing experiments, and language-model agents that search literature, write code, or coordinate tests. The field is moving from passive pattern fitting toward systems that propose hypotheses, design informative measurements, revise models when evidence disagrees, and verify results. A central challenge is that accurate predictions or plausible equations do not guarantee recovered mechanisms or genuinely new insight, so evaluations increasingly test robustness, evidence grounding, experimental efficiency, and uncertainty.

Latest papers

CardsList

86 papers18 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

  1. Can LLMs Uncover Hidden Physical Laws through Free Exploration?

    Oct 27, 2026Zhen Yang, Wen Wang, Xander Xu +1AI Agents for Scientific DiscoveryLarge Language Model-Guided Scientific Discovery

    HKUST(GZ) · ZJU · Alibaba Group +1

  2. Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own Discoveries Are Statistical

    Oct 23, 2026Wenbin Mao, Pei ZouScientific DiscoveryAutonomous Scientific Discovery

    Artificial Intelligence Laboratory, Hooman Biotechnology (Beijing) Co., Ltd.

  3. AgenticEvolve: Evolutionary Program Search with Persistent Language Model Agents that Design and Run Experiments

    Oct 22, 2026Ze-Yu Peng, Qing-Yu Lan, Zhan-He Wang +2LLMs for Evolutionary OptimizationLLM-Based Program Synthesis

    School of Physical Sciences, University of Chinese Academy of Sciences, Beijing 100049, China. · International Centre for Theoretical Physics Asia-Pacific, University of Chinese Academy of Sciences, Beijing 100190, China. · Taiji Laboratory for Gravitational Wave Universe, University of Chinese Academy of Sciences, Beijing 100049, China. +2

  4. Bayesian Model Discovery with Language Models: Closing the Loop between Hypotheses and Experiments

    Oct 19, 2026JooKyung Yuh, Byungmin Park, Eunseo Choi +6Scientific DiscoveryLarge Language Model-Guided Scientific Discovery

    Korea University · KAIST · KETI

  5. Knowledge Manifold Optimization for Scientific Discovery

    Oct 19, 2026Shigeru Obayashi, Yoshiaki Kawagoe, Kazuhiko Komatsu +1Scientific DiscoveryScientific Hypothesis Generation

    Institute of Fluid Science, Tohoku University, 2-1-1 Katahira, Aoba-ku, Sendai, Miyagi 980-8577, Japan · Department of Aerospace Engineering, Tohoku University, 6-6-01, Aoba, Aramaki, Aoba-ku, Sendai, Miyagi 980-8579, Japan · Research Center for Green X-Tech, Tohoku University, 6-6-11, Aoba, Aramaki, Aoba-ku, Sendai, Miyagi 980-8579, Japan +1

  6. From Flow-Box Invariants to Global Conservation Laws: Machine Learning-Assisted Detection of Singularities and Near-Integrability

    Oct 16, 2026Jimmie Adriazola, Ioannis G. Kevrekidis, Panayotis G. Kevrekidis +1Dynamical SystemsScientific Discovery

    School of Mathematical and Statistical Sciences, Arizona State University, Tempe, AZ 85287, USA · Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD 21218, USA · Department of Mathematics and Statistics, University of Massachusetts Amherst, Amherst, MA 01003-4515, USA +1

  7. Null Controls Are Necessary but Not Sufficient: Evaluating Acceptance Guards for Scientific Discovery and Interpretability

    Oct 15, 2026Tianyu WuScientific DiscoveryAutomated Evaluation

    Project Aether

  8. Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBench

    Oct 13, 2026Yuxiao Hu, Qian Li, Ding Wang +4Scientific DiscoveryAI Agents for Scientific Discovery

    The Hong Kong Polytechnic University, Hong Kong, China · Eastern Institute of Technology, Ningbo, China · Shanghai Jiao Tong University, Shanghai, China +1

  9. Coupled Harness--Model Evolution for Scientific Equation Discovery

    Oct 13, 2026Pengze Li, Jiaquan Zhang, Encheng Su +8Large Language Model-Guided Scientific DiscoveryScientific Discovery

    Fudan University · Shanghai Artificial Intelligence Laboratory · University of Science and Technology of China +4

  10. RSI-Anything: Unlocking Recursive Self-Improvement with World Models

    Oct 9, 2026Taoyong Cui, Pinxian Zeng, Wanghan Xu +8Recursive Self-ImprovementSelf-Improving Agents

  11. EvoSim: Learning to Model, Modeling to Learn

    Oct 8, 2026Yun-Wei Song, Jinkai Tao, Jun-Dong Zhang +3Autonomous Scientific DiscoveryPhysics-Based Simulation

    Beijing Key Laboratory of Complex Solid-State Batteries, Department of Chemical Engineering, Tsinghua University, Beijing, China · State Key Laboratory of Chemical Engineering and Low-Carbon Technology, Tsinghua University, Beijing, China · Beijing Tsingyu Technology Co., Ltd., Beijing, China +5

  12. Open-ended Scientific Discovery with Possibilistic Reasoning

    Oct 8, 2026Anita Yang, Siu Lun Chau, Tomoya Wakayama +2Scientific DiscoveryAutonomous Scientific Discovery

    Lattice Lab, Toyota Motor Corporation, Japan · Department of Computer Science, University of Tokyo, Japan · EPIC Lab, College of Computing & Data Science, Nanyang Technological University, Singapore +2

  13. SciExam for ENSO: Can AI Agents Build Climate Models?

    Oct 7, 2026Yinling Zhang, Langchen Liu, Dongbin Xiu +4AI for ScienceAI Agent Benchmarks

    The Ohio State University · Yale University · University of California, San Diego +2

  14. Learning to Outgrow a Theory: Experimental Discovery Beyond the Initial Hypothesis Space

    Oct 6, 2026SiYuan Ma, Albert Gao, Chunzheng Zhu +6Scientific DiscoverySequential Hypothesis Testing

    Nanyang Technological University · Carnegie Mellon University · Hunan University +5

  15. Explore, Then Commit: Measurement-Efficient Scientific Law Discovery with Language Models

    Oct 6, 2026Kautik Mandve, Dileepa FernandoScientific DiscoveryScientific Hypothesis Generation

    Vernon Hills High School, Vernon Hills, Illinois, USA · Information Systems Technology and Design Singapore University of Technology and Design, Singapore

  16. EurekaBench: Measuring Agentic Ability to Discover New Scientific Insights

    Sep 30, 2026Jiayi Geng, Zhengxuan Wu, Kevin S. Chen +12Scientific DiscoveryLong-Horizon Agent Evaluation

    Carnegie Mellon University, Language Technologies Institute · Stanford University, Department of Computer Science · Yale University, Quantitative Biology Institute +8

  17. How AI Agents Discover Scientific Equations: From Hydrotope Rediscovery to New Water-Wave Amplitudes

    Sep 30, 2026Zihan Zhou, Digvijay Wadekar, Matias ZaldarriagaAI Agents for Scientific DiscoveryScientific Discovery

    Department of Physics, Princeton University, Princeton, NJ 08540, USA · Center for Gravitational Physics, University of Texas at Austin, Austin, TX 78712, USA · School of Natural Sciences, Institute for Advanced Study, 1 Einstein Drive, Princeton, NJ 08540, USA

  18. MechBench: Can AI Scientific Agents Discover Mechanisms Beyond Phenomenal Laws?

    Sep 28, 2026Zihan Yu, Jiadong Zhang, Jialin Cheng +2Scientific DiscoveryAI Agent Benchmarks

    Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China · Beijing Zhongguancun Academy, Beijing, China +2

  19. NeuronDiscover: Agent-in-Twin for Mechanistic Discovery in Neuronal Microenvironments with World Action Models

    Sep 28, 2026Haowei Xu, Wanyi Fu, Hongbin Han +1AI Agents for Scientific DiscoveryScientific Discovery

    Institute of Medical Technology, Peking University Health Science Center, Beijing, China · Beijing Key Laboratory of Intelligent Neuromodulation and Brain Disorder Treatment, Beijing, China · Department of Radiology, Peking University Third Hospital, Beijing, China +1

  20. ALDER: Discovering the Laws of a World by Acting in It

    Sep 27, 2026Teng Cao, Yu Deng, Quentin Delfosse +1Scientific DiscoveryAction-Conditioned World Models

    Technische Universität Darmstadt · Intrinsic · CS Department, TU Darmstadt +2

  21. Discovering Symmetries in Neural Network Parameter Spaces

    Sep 27, 2026Bo Zhao, Nima Dehmamy, Robin Walters +1Scientific DiscoverySymmetry Discovery

    Harvard University · IBM Research · Northeastern University +1

  22. Equation discovery with Bayesian tree-adjoining grammars

    Sep 25, 2026Christopher A. Lindley, Nikolaos Dervilis, Keith WordenNonlinear System IdentificationScientific Discovery

    Dynamics Research Group University of Sheffield Mappin St, Sheffield, UK

  23. MOSAIC-SR: Transformer-Guided Symbolic Regression for Scientific Equation Recovery

    Sep 17, 2026Peiyi Zheng, Yanming Kang, Hans De Sterck +1Symbolic RegressionScientific Discovery

    University of Waterloo

  24. Geometric Signatures of Conceptual Reorganization: A Counterfactual Embedding Framework for Detecting Scientific Revolutions

    Sep 14, 2026Dimitris Ntounis, Ariel Schwartzman, Chris Chafe +1Scientific DiscoverySemantic Change Detection

    Department of Physics, Stanford University, Stanford, CA, USA · SLAC National Accelerator Laboratory, Menlo Park, CA, USA · Department of Music, Stanford University, Stanford, CA, USA +1

  25. Symmetry Discovery in Quantum Learning: Observable-Level and Task-Level Inference from Finite Measurements

    Sep 11, 2026Zeyu ChenSymmetry DiscoveryQuantum Machine Learning

  26. LATS: Levy Adaptive Tree Sampling for Feedback-Driven Diverse Target Discovery

    Sep 6, 2026Binglin Ji, Anindya Sarkar, Hengchang Lu +3Adaptive SamplingDiffusion Sampling

    Department of CSE, Washington University in St.Louis, USA

  27. Can LLMs Discover Scientific Laws in Real and Parallel Worlds?

    Sep 1, 2026Yiming Huang, Ziche Liu, Junxia Cui +11Scientific DiscoveryScientific Hypothesis Generation

    University of California San Diego · University of California, Irvine · Cushing Academy +1

  28. EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation

    Sep 1, 2026Qing Zhao, Haowei Li, Weijian Deng +3Belief RevisionStructural Causal Models

    Sun Yat-sen University · Tsinghua Shenzhen International Graduate School, Tsinghua University

  29. SCoR: A Hierarchical Framework for Forecasting Relations Between Scientific Concepts

    Aug 27, 2026Jingze Wang, Fred Sun, Shangqi GuoScientific DiscoveryTemporal Link Prediction

    Center for Brain-Inspired Computing Research, Tsinghua University

  30. Correcting a learned physical invariant improves world-model rollouts

    Aug 24, 2026Richard BaoWorld ModelsWorld Model Learning

    Independent Researcher