AI Agents for Scientific Discovery

Ask about this topic

Overview

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

CardsList

288 papers57 papers in the last four weeks, up 111% on the four weeks before. 0.3% 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. Infinity Machine: a self-improving AI agent for research

    Oct 26, 2026Harish Santhanalakshmi GanesanAutonomous Research AgentsAI Agents for Scientific Discovery

    Independent researcher

  3. EmbodiedLab: Benchmarking Embodied Agents That Act to Know

    Oct 26, 2026Hongcheng Gao, Zelin Zheng, Alex Zhou +18Embodied Agent BenchmarksAI Agents for Scientific Discovery

    HexaFuture Inc. · Tsinghua University · Peking University +1

  4. SEEK: Skill Extraction with Evolving Knowledge against Frontier Science Agents

    Oct 25, 2026Cheng Gui, Xiang Zheng, Yutao Wu +5AI Agent SecurityAgent Skill Security Auditing

    City University of Hong Kong, Hong Kong · Hong Kong Institute of AI for Science, Hong Kong · Deakin University, Australia +2

  5. LegoSR: A Unified Framework for Self-improving Agent-Guided Scientific Discovery

    Oct 24, 2026Hao Mao, Xu T. Liu, Peng Zhao +2AI Agents for Scientific DiscoverySymbolic Regression

    The Hong Kong Polytechnic University, Hong Kong SAR, China · Eastern Institute of Technology, Ningbo, China · Amazon Web Services, Seattle, USA +3

  6. Distill, Debate, Discover: Grounding Multi-Agent Research Ideation in Graph-Distilled Insights

    Oct 23, 2026Qianran Ma, Muxin Liu, Grace Kim +2Research Idea GenerationAI Agents for Scientific Discovery

    University of Pennsylvania

  7. POSEIDON: Scaling Training Environments for Scientific Agents from Code Repositories

    Oct 23, 2026Qifan Zhang, Yuhan Li, Nuo Chen +8AI Agents for Scientific DiscoveryLLM Agent Training

    The Hong Kong University of Science and Technology (Guangzhou) · Hunyuan Team, Tencent

  8. PULSES: multi-agent AI for autonomous excited-state model building and dynamics

    Oct 23, 2026Fangning Ren, Lechen Dong, Xu Chen +3AI Agents for Scientific DiscoveryAutonomous Research Agents

    Department of Chemistry, Emory University, Atlanta, GA, 30322, USA

  9. PersonaScienceBench: Evaluating Scientific Agents with Diverse Simulated Researchers

    Oct 23, 2026Siyang Wu, Weizhi Zhang, Chen Yang +29Scientific Agent BenchmarksLLM Agent Evaluation

    University of Chicago · University of Illinois Chicago · Harvard University +15

  10. FrontierCS 2: A Benchmark for Computer Science R&D

    Oct 21, 2026Qiuyang Mang, Wenhao Chai, Runyuan He +58Scientific Agent BenchmarksCoding Agent Benchmarks

  11. ExpEvolve: Structuring and Reusing Experience for Open-Ended Discovery

    Oct 21, 2026Yongqiang Chen, Chenxi Liu, Deyu Zou +4AI Agents for Scientific DiscoveryLarge Language Model-Guided Scientific Discovery

    MBZUAI · Carnegie Mellon University · TMLR Group, Hong Kong Baptist University +2

  12. Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?

    Oct 20, 2026Ming Zhong, Stacy Li, Nicholas Carlini +1AI Agents for Scientific DiscoveryScientific Agent Benchmarks

    Anthropic Fellows Program · Anthropic

  13. GBClaw: An agentic AI framework for atomistic grain boundary research and mechanistic discovery

    Oct 20, 2026Yazhuo Liu, Kunqing Ding, Xiaoguo Gong +8Materials ScienceAI Agents for Scientific Discovery

    Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA, 30332, USA · Department of Mechanical Science and Bioengineering, Graduate School of Engineering Science, The University of Osaka, Osaka, 560-8531, Japan · Department of Aerospace and Mechanical Engineering, University of Southern California, Los Angeles, CA, USA +2

  14. Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition

    Oct 20, 2026Wenjie Lou, Tianshuo Peng, Shiyang Feng +96Long-Horizon LLM AgentsAI Agents for Scientific Discovery

  15. Modeling Authentic Research Trajectories: A Graph View of Research Ideation

    Oct 19, 2026Ruochen Li, Zhiyu ChenResearch Idea GenerationAI Agents for Scientific Discovery

    Department of Computer Science, University of Texas at Dallas

  16. Magnolia: A Persistent-Memory Agent Framework for Computational Chemistry

    Oct 19, 2026Tao Jiang, Benjamin Navet, Yousouf Taghzouti +3AI Agents for Scientific DiscoveryMemory-Augmented Language Model Agents

    Université Côte d’Azur, CNRS, ICN, Nice, France · Inria, Université Côte d’Azur, CNRS, I3S, France

  17. Explore or Confirm? LLM Agents Misallocate Measurements Under Noise

    Oct 18, 2026Abdul Karim, Matt KeonAI Agents for Scientific DiscoveryExploration-Exploitation Tradeoff

    Xstendyl

  18. Epi: Towards a Persistent, Self-Improving Agent for Autonomous Research

    Oct 18, 2026Yue Huang, Zhangchen Xu, Xiaonan Luo +16Operations ResearchAutonomous Research Agents

    Bake AI · University of Notre Dame · University of Washington +10

  19. Aptamers as a sandbox for lab-in-the-loop agentic molecular discovery

    Oct 17, 2026Zachary Cutts, John Coller, Rachel Chen +9AI Agents for Scientific DiscoveryMolecule Design

    Google Research · Department of Genetics, Stanford University, Stanford, CA, USA · Google Cloud +1

  20. TCMScience: An Autonomous Scientist for Traditional Chinese Medicine

    Oct 17, 2026Yanlan Kang, Ruiqi Liu, Xinpei Gu +4AI Agents for Scientific DiscoveryScientific Workflow Automation

    Institute of Medical Philosophy & Future AI (IMPF-AI) · Shanghai Medical College, Fudan University · Guangdong Provincial Key Laboratory of New Drug Screening and Guangdong–Hong Kong–Macao Joint Laboratory for New Drug Screening, School of Pharmaceutical Sciences, Southern Medical University +4

  21. At the Limits of Computability: Steps Towards Autonomous AI Discovery on the Busy Beaver Frontier

    Oct 15, 2026Marco Dos Santos, Vivek Veeriah, Alex Havrilla +4Autonomous Scientific DiscoveryAI Agents for Scientific Discovery

    Google DeepMind · University of Cambridge

  22. From Research Goals to Scientific Closure: Evaluating Agents Through Evidence-Supported Physics Research

    Oct 15, 2026Yijia Mao, Song Dai, Tao Chen +14Scientific Agent BenchmarksAI Agents for Scientific Discovery

    Shanghai AI Laboratory · Shanghai Jiao Tong University · The HongKong University of Science and Technology(Guangzhou) +1

  23. Scaling Discovery Requires Forgetting

    Oct 14, 2026Shangyin Tan, Ben Zhou, Lakshya A Agrawal +8AI Agents for Scientific DiscoveryLLM Agent Memory

    UC Berkeley · Stanford · Bespoke Labs

  24. SwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm

    Oct 14, 2026Qianru Meng, Xi Zhang, Konstantinos Papakostas +9AI Agents for Scientific DiscoveryRecursive Self-Improvement

    Huawei Technologies Co., Ltd. · Leiden University · University of Groningen

  25. Into the Unknown: Benchmarking AI agents on open scientific research problems

    Oct 13, 2026Seungone Kim, Jiayi Geng, Young-Jun Lee +25Scientific Agent BenchmarksAI-Assisted Scientific Research

    Carnegie Mellon University · University of Minnesota · Stanford University +13

  26. 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

  27. The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery

    Oct 13, 2026Robert Tjarko Lange, Luca Grillotti, Yutaro Yamada +2AI Agents for Scientific DiscoveryAI-Assisted Scientific Research

    Sakana AI

  28. Drafting Agents, Not Just Tokens: Speculative Recursive Self-Improvement for Agentic Systems

    Oct 12, 2026Xin Xu, Ke Cheng, Hao Wang +11LLM Agent Self-ImprovementRecursive Self-Improvement

    Tencent AMS, Beijing, China · State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University, Beijing, China · CCSE lab, Beihang University. +3

  29. SLDBench v2: Active Scaling Law Discovery

    Oct 12, 2026Lingbei Meng, Rui Huang, Zhirong Shen +5AI Agents for Scientific DiscoveryLanguage Model Scaling Laws

    The Chinese University of Hong Kong, Shenzhen · The University of Hong Kong · University of Electronic Science and Technology of China +2

  30. Triage-PiEvo: Evidence Admission for Principle-Evolving Scientific Agents

    Oct 10, 2026Peize Li, Yingming Pu, Xingguo Xu +3AI Agents for Scientific DiscoveryLarge Language Model-Guided Scientific Discovery

    Westlake University · Kuaishou Technology · Zhejiang University +2