AI Agents for Scientific Discovery

Follow this topic Ask about this topic

AI agents for scientific discovery aim to help researchers move from questions and hypotheses to analysis, experiments, and evidence-backed conclusions. Common approaches combine language models with literature retrieval, code execution, scientific simulators, laboratory instruments, and specialized agents in iterative hypothesis–test–revision loops. Work spans fields such as materials science, biology, physics, chemistry, and mathematics, with systems also developing reusable skills and memories to build on prior results. A central challenge is ensuring that promising outputs are genuinely novel, scientifically valid, reproducible, and grounded in evidence, especially in long workflows and physical experiments.

Latest papers

292 papers57 papers in the last four weeks, up 111% on the four weeks before. 0.3% of all new papers.

Site4Drug: Predicting Drug-Binding Target Sites with an AI Agent
Jun 1, 2026Taehan Kim, Sarrah Rose Mikhail Leung, Bharat Mekala +1AI Agents for Scientific Discovery Drug Discovery
UC Berkeley · University of Michigan
Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence
May 31, 2026Fiona Y. Wang, Markus J. BuehlerAI Agents for Scientific Discovery Autonomous Scientific Discovery
Laboratory for Atomistic and Molecular Mechanics Department of Biological Engineering Massachusetts Institute of Technology Cambridge, MA 02139, USA · Laboratory for Atomistic and Molecular Mechanics Department of Civil and Environmental Engineering Department of Mechanical Engineering Center for Computational Science and Engineering Schwarzman College of Computing Massachusetts Institute of Technology Cambridge, MA 02139, USA
CodeCytos: AI-assisted spatial molecular imaging analysis via code-augmented agent action space
May 30, 2026Hung Q. Vo, Huy Q. Vo, Son T. Ly +6Computational Pathology Spatial Transcriptomics
University of Houston, Department of Electrical and Computer Engineering, Houston, Texas, 77004, USA · Houston Methodist Hospital, Department of Systems Medicine and Biomedical Engineering, Houston, Texas, 77030, USA
Learning to Choose: An Empowerment-Guided Multi-Agent System with semantic communication for Adaptive Method Selection
May 28, 2026Geremy Loachamín-Suntaxi, Robert Lazar, Dimitrios G. Giovanis +2Multi-Agent LLM Systems AI Agents for Scientific Discovery
School of Chemical Engineering, National Technical University of Athens, Zographos Campus, 15780, Attiki, Greece · Luxembourg Institute of Science and Technology Esch-sur-Alzette, L-4362, Luxembourg
Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent
May 28, 2026Yiming Liu, Bin Lu, Meng Jin +6AI Agents for Scientific Discovery Document Information Extraction
School of Information Science and Electronic Engineering, Shanghai Jiao Tong University, Shanghai, China · School of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China · State Key Laboratory of Estuarine and Coastal Research, East China Normal University, Shanghai, China +2
Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter Estimation
May 28, 2026Jiawei Chen, Xiaofan Gui, Shikai Fang +4AI Agents for Scientific Discovery Large Language Model-Guided Optimization
Peking University Beijing, China · Microsoft Research Beijing, China · Chalmers University of Technology Gothenburg, Sweden
DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability
May 28, 2026Ziyue Yang, Da Ma, Hanqi Li +8AI for Science AI Agents for Scientific Discovery
X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · Suzhou Laboratory, Suzhou, China · Shanghai Innovation Institution, Shanghai, China +1
First head-to-head comparison of agentic AI applied to the analysis of simulated data of the Einstein Telescope
May 27, 2026Gianluca IngugliaAI Agents for Scientific Discovery AI Agent Evaluation
Marietta Blau Institute for Particle Physics, Austrian Academy of Sciences, 1010 Vienna, Austria
Closed-Loop Molecular Design with Calibrated Deference
May 27, 2026Newman Cheng, Gordon Broadbent, Jason Dong +11Molecular Optimization AI Agents for Scientific Discovery
Microsoft Discovery & Quantum, Redmond, WA, USA. · Department of Chemical and Environmental Engineering, Yale University, New Haven, CT, USA. · CanAm Bioresearch Inc., Winnipeg, MB, Canada. +1
AtomComposer: Discovering Chemical Space from First Principles with Reinforcement Learning
May 27, 2026Bjarke Hastrup, Francois Cornet, Tejs Vegge +1AI Agents for Scientific Discovery 3D Molecular Generation
Dept. of Energy Conversion and Storage, Technical University of Denmark, Denmark · Dept. of Applied Mathematics and Computer Science, Technical University of Denmark, Denmark · Pioneer Center for Accelerating P2X Materials Discovery (CAPeX), Kgs. Lyngby, Denmark
AI Research Agents Narrow Scientific Exploration
May 27, 2026Yixuan Tang, Yi YangAI Agents for Scientific Discovery AI Agent Evaluation
1*ISOM, The Hong Kong University of Science and Technology.
AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models
May 27, 2026Ruiyi Zhang, Peijia Qin, Qi Cao +2Continual Learning for LLM Agents AI Agents for Scientific Discovery
Department of Electrical and Computer Engineering, University of California San Diego, La Jolla, CA 92093, USA · Department of Medicine, University of California San Diego, La Jolla, CA 92093, USA
PolyFusionAgent: A Multimodal Foundation Model and Autonomous AI Assistant for Polymer Property Prediction and Inverse Design
May 26, 2026Manpreet Kaur, Xingying Zhang, Qian LiuAI Agents for Scientific Discovery Materials Property Prediction
Department of Applied Computer Science, The University of Winnipeg, 515 Portage Avenue, Winnipeg, MB R3B 2E9, Canada. · Department of Mechanical Engineering, University of Manitoba, Winnipeg, MB R3T 2N2, Canada.
AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery
May 22, 2026Guiyao Tie, Jiawen Shi, Dingjie Song +20AI Agents for Scientific Discovery Scientific Workflow Automation
Huazhong University of Science and Technology · Lehigh University · Wuhan University +13
Toward AI VIS Co-Scientists: A General and End-to-End Agent Harness for Solving Complex Data Visualization Tasks
May 20, 2026Haichao Miao, Zhimin Li, Kuangshi Ai +4Scientific Visualization Data Visualization
Lawrence Livermore National Laboratory · Vanderbilt University · University of Notre Dame
AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows
May 19, 2026Shuaike Shen, Wenduo Cheng, Shike Wang +2Multi-Agent Orchestration AI Agents for Scientific Discovery
1Ray and Stephanie Lane Computational Biology Department, School of Computer Science, Carnegie Mellon University · 2Machine Learning Department, School of Computer Science, Carnegie Mellon University
Agentic Discovery of Cryomicroneedle Formulations
May 19, 2026Hao Li, Lifu Du, Nurul Hameed +3AI Agents for Scientific Discovery
Department of Biomedical Engineering, City University of Hong Kong 83 Tat Chee Avenue, Kowloon, Hong Kong SAR, China
Harnessing AtomisticSkills for Agentic Atomistic Research
May 18, 2026Bowen Deng, Bohan Li, Matthew Cox +20AI Agents for Scientific Discovery AI Coding Agents
Department of Materials Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139, USA · Department of Chemistry, Kookmin University, Seoul 02707, Republic of Korea +5
Qumus: Realization of An Embodied AI Quantum Material Experimentalist
May 18, 2026Lihan Shi, Zhaoyi Joy Zheng, Xinzhe Juan +14AI Agents for Scientific Discovery Materials Science
Department of Physics, Princeton University, Princeton, New Jersey 08544, USA · Department of Electrical and Computer Engineering, Princeton University, Princeton, New Jersey 08544, USA · Department of Computer Science and Engineering, University of Michigan, Ann Arbor, Michigan 48109, USA +5
STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery
May 18, 2026Jiarui Su, Songjun Tu, Bei Sun +1LLM Self-Refinement AI Agents for Scientific Discovery
Central South University · Institute of Automation, Chinese Academy of Sciences · Pengcheng Laboratory
FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics
May 17, 2026Qiran Zou, Hou Hei Lam, Wenhao Zhao +11AI Agents for Scientific Discovery Inference-Time Search
National University of Singapore · Tsinghua University · University of Minnesota +2
ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery
May 16, 2026Haofei Yu, Jiaxuan You, Peter Clark +2AI Agents for Scientific Discovery Link Prediction
University of Illinois Urbana-Champaign · Allen Institute for AI
DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
May 14, 2026Yikun Zhang, Xiwei Cheng, Tianyu Liu +2AI Agents for Scientific Discovery AI-Assisted Scientific Research
1Northeastern University · 2Broad Institute of MIT and Harvard · 3Yale University +1
Beyond AI as Assistants: Toward Autonomous Discovery in Cosmology
May 14, 2026Licong Xu, Thomas BorrettMulti-Agent LLM Systems AI Agents for Scientific Discovery
Institute of Astronomy, University of Cambridge, Madingley Road, Cambridge CB3 0HA, UK · Kavli Institute for Cosmology, University of Cambridge, Madingley Road, Cambridge CB3 0HA, UK · Cavendish Astrophysics, University of Cambridge, Madingley Road, Cambridge CB3 0HA, UK
Lang2MLIP: End-to-End Language-to-Machine Learning Interatomic Potential Development with Autonomous Agentic Workflows
May 14, 2026Wenwen Li, Yuki Orimo, Nontawat CharoenphakdeeMulti-Agent LLM Systems AI Agents for Scientific Discovery
Preferred Networks, Inc., Tokyo, Japan.
Sheaf-Theoretic Transport and Obstruction for Detecting Scientific Theory Shift in AI Agents
May 13, 2026David N. Olivieri, Roque J. HernándezAI Agents for Scientific Discovery Sheaf Theory
Universidade de Vigo, Department of Computer Science (LSI), Spain
Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction
May 13, 2026Darius A. Faroughy, Sofia Palacios Schweitzer, Ian Pang +2AI Agents for Scientific Discovery AI Agent Evaluation
New High Energy Theory Center Department of Physics & Astronomy Rutgers University · Faculty of Computing & Data Sciences Boston University
OpenAaaS: An Open Agent-as-a-Service Framework for Distributed Materials-Informatics Research
May 13, 2026Peng Kang, Bixuan Li, Xiaoya Huang +5Multi-Agent Orchestration AI Agents for Scientific Discovery
National Key Laboratory of AI for Materials Science Beihang University Beijing, China · Tianmushan Laboratory Beihang University Beijing, China
ToolMol: Evolutionary Agentic Framework for Multi-objective Drug Discovery
May 12, 2026Andrew Y. Zhou, Sharvaree Vadgama, Sumanth Varambally +3Drug Discovery AI Agents for Scientific Discovery
Department of Computer Science and Engineering, UC San Diego, La Jolla, California, United States · Department of Computer Science, Stanford University, Stanford, California · Skaggs School of Pharmacy and Pharmaceutical Sciences, UC San Diego, La Jolla, California
GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms
May 11, 2026Juan Diego Toscano, Zhaojie Chai, George Em KarniadakisAI Agents for Scientific Discovery Automated Algorithm Discovery
Division of Applied Mathematics, Brown University, Providence, 02912, RI, USA

Jun 1, 2026J/K move · Enter open · S save

Site4Drug: Predicting Drug-Binding Target Sites with an AI Agent

Taehan Kim, Sarrah Rose Mikhail Leung, Bharat Mekala, Jeongbin Park

UC Berkeley · University of Michigan

AI Agents for Scientific Discovery Drug Discovery

Open paper AskPDF arXiv

Selecting where to intervene on a protein (i.e., choosing a targetable site) is often a more ambiguous and failure-prone bottleneck than selecting what binds, especially for membrane proteins where accessibility, topology, and post-translational modifications (PTMs) constrain actionable regions. We present Site4Drug, a modality-aware site-finding agent that outputs a ranked list of targetable regions with explicit constraints, evidence summaries, risk flags, and a traceable decision log. Rather than requiring users to specify the drug modality upfront, Site4Drug can recommend a binding modality (e.g., antibody/peptide-like vs small-molecule) from the same evidence used for site discovery, including topology, hydropathy, PTM propensity, disulfides, domain context, and sequence. Importantly, this evidence is applied consistently across modalities, including small-molecule pocket discovery, to avoid selecting chemically plausible but biologically occluded sites.