README.md

Awesome AI Scientist Papers

Welcome to the Awesome AI Scientist Papers repository! This project aims to curate a collection of important papers to the field of AI/Robot Scientist.

Scaling Laws in Scientific Discovery with AI Scientists and Robot Scientists.

Table of Contents

• Papers
• Survey
• News
• Benchmark
• Cite

Papers

• Can AI Scientists Coordinate at Runtime?, Zijian Liu, Yangzhixin Luo, Junyu Lu et al., arXiv, 2026

• The AutoResearch Moment: From Experimenter to Research Director, Chaoyue He, Xin Zhou, Di Wang et al., Preprints, 2026

• AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing, Jianda Du, Youran Sun, Haizhao Yang, arXiv, 2026

• Democratizing Discovery: How Automated Research Pipelines Make Scientific Innovation Universally Accessible, Euan, Zenodo, 2026

• CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery, Ao Qu, Han Zheng, Zijian Zhou et al., arXiv, 2026

• Scaling Laws in Scientific Discovery with AI and Robot Scientists, Pengsong Zhang, Heng Zhang et al., arXiv, 2025

• Towards Data-Centric Automatic R&D, Haotian Chen et al., arXiv, 2024

• Mlr-copilot: Autonomous machine learning research based on large language models agents, Ruochen Li et al., arXiv, 2024

• Towards end-to-end automation of AI research, Chris Lu et al., Nature, 2026

• Autonomous Generalist Scientist: Towards and Beyond Human-Level Scientific Research with Agentic and Embodied AI and Robots, Pengsong Zhang, Heng Zhang et al., ResearchGate, 2024

• ChatGPT as Research Scientist: Probing GPT’s capabilities as a Research Librarian, Research Ethicist, Data Generator, and Data Predictor, Steven A. Lehr et al., PNAS, 2024

Autonomous Literature Review

• LLM-assisted systematic review of large language models in clinical medicine, Sully F. Chen et al., Nature Medicine, 2026

• Empowering biomedical evidence exploration and synthesis with deep knowledge graph research, Zifeng Wang et al., Nature Machine Intelligence, 2026

• SurveyX: Academic Survey Automation via Large Language Models, Xun Liang et al., arXiv, 2025

• PaSa: An LLM Agent for Comprehensive Academic Paper Search, Yichen He et al., arXiv, 2025

• SCILITLLM: HOW TO ADAPT LLMS FOR SCIENTIFIC LITERATURE UNDERSTANDING, Sihang Li et al., arXiv, 2024

• AutoSurvey: Large Language Models Can Automatically Write Surveys, Wenjin Yao et al., arXiv, 2024

• LLMs4Synthesis: Leveraging Large Language Models for Scientific Synthesis, Hamed Babaei Giglou et al., arXiv, 2024

• PubTator 3.0: an AI-powered literature resource for unlocking biomedical knowledge, Chih-Hsuan Wei et al., Nucleic Acids Research, 2024

• PubMed and beyond: biomedical literature search in the age of artificial intelligence, Qiao Jin et al., eBioMedicine, 2024

Proposal, Idea Generation

• XunZi, an AI biologist, reveals disease-modifying targets, Xinhe Huang et al., Nature Biomedical Engineering, 2026

• Predicting new research directions in materials science using large language models and concept graphs, Thomas Marwitz et al., Nature Machine Intelligence, 2026

• AgentRxiv: Towards Collaborative Autonomous Research, Samuel Schmidgall et al., arXiv, 2025

• Agent Laboratory: Using LLM Agents as Research Assistants, Samuel Schmidgall et al., arXiv, 2025

• An empirical investigation of the impact of ChatGPT on creativity, Byung Cheol Lee et al., Nature Human Behaviour, 2024

• Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas, Xiang Hu et al., arXiv, 2024

• Two Heads Are Better Than One: A Multi-Agent System Has the Potential to Improve Scientific Idea Generation, Haoyang Su et al., arXiv, 2024

• Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers, Chenglei Si et al., arXiv, 2024

• ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models, Jinheon Baek et al., arXiv, 2024

• Forecasting high-impact research topics via machine learning on evolving knowledge graphs, Xuemei Gu et al., arXiv, 2024

• Large Language Models are Zero Shot Hypothesis Proposers, Biqing Qi et al., arXiv, 2023

• SciMON: Scientific Inspiration Machines Optimized for Novelty, Qingyun Wang et al., arXiv, 2023

Virtual, Digital, Agent, Experimentation

• The Virtual Biotech: A multi-agent AI framework for therapeutic discovery and development, Harrison G. Zhang et al., Science, 2026

• Discovering algorithms with computational language processing, Théo Bourdais et al., Science Advances, 2026

• Large language models as uncertainty-calibrated optimizers for experimental discovery, Bojana Ranković et al., Nature Machine Intelligence, 2026

• An enzyme-specific protein language model for catalytic property prediction, Chong Wang et al., Nature Communications, 2026

• A knowledge graph framework for digital twins of chemical processes, Shuyuan Zhang et al., Nature Chemical Engineering, 2026

• AI-guided design of efficient perovskite solar cells operationally stable at 100°C, Jiahao Guo et al., Science, 2026

• A conversational multi-agent AI system for automated plant phenotyping, Feng Chen et al., Nature Communications, 2026

• Empowering AI data scientists using a multi-agent LLM framework with self-evolving capabilities for autonomous, tool-aware biomedical data analyses, Dechao Bu et al., Nature Biomedical Engineering, 2026

• An end-to-end framework for reactivity in heterogeneous catalysis, Santiago Morandi et al., Nature Chemical Engineering, 2026

• Meta-designing quantum experiments with language models, Sören Arlt et al., Nature Machine Intelligence, 2026

• SciSciGPT: advancing human–AI collaboration in the science of science, Erzhuo Shao et al., Nature Computational Science, 2026

• Generative discovery of partial differential equations by learning from math handbooks, Hao Xu et al., Nature Communications, 2025

• Multimodal learning enables chat-based exploration of single-cell data, Moritz Schaefer et al., Nature Biotechnology, 2025

• A multi-agentic framework for real-time, autonomous freeform metasurface design, Robert Lupoiu et al., Science Advances, 2025

• A neural symbolic model for space physics, Jie Ying et al., Nature Machine Intelligence, 2025

• Reimagining research papers as interactive and reliable AI agents, Jiacheng Miao et al., Nature, 2026

• A collaborative agent with two lightweight synergistic models for autonomous crystal materials research, Tongyu Shi et al., Nature Machine Intelligence, 2026

• MutexaGPT: an intuition-to-design translator for physics-based enzyme engineering, Qianzhen Shao et al., Nature Computational Science, 2026

• Autonomous biomedical research with an artificial intelligence agent, Kexin Huang et al., Science, 2026

• Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy, Youran Sun et al., arXiv, 2026

• AutoZyme: An Autonomous Agentic Framework to Optimize Bioinformatics Software, Elliot Xie et al., bioRxiv, 2026

• An AI Co-Data-Scientist for Prioritizing Candidate Biomarkers from Wearable Sensor Data, Yubin Kim et al., arXiv, 2026

• An AI system to help scientists write expert-level empirical software, Eser Aygün et al., Nature, 2026

• A multi-agent system for automating scientific discovery, Ali E. Ghareeb et al., Nature, 2026

• Accelerating scientific discovery with Co-Scientist, Juraj Gottweis et al., Nature, 2026

• An agentic framework for autonomous scientific discovery in cancer pathology, Florian Trost et al., Nature Medicine, 2026

• Bridging electron microscopy and materials analysis with an autonomous agentic platform, Guangyao Chen, Wenhao Yuan, Fengqi You, Science Advances, 2026

• Towards end-to-end automation of AI research, Chris Lu et al., Nature, 2026

• CellVoyager: AI CompBio agent generates new insights by autonomously analyzing biological data, Samuel Alber et al., Nature Methods, 2026

• CASSIA: a multi-agent large language model for automated and interpretable cell annotation, Elliot Xie et al., Nature Communications, 2026

• The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies, Kyle Swanson et al., Nature, 2025

• aiXiv: A Next-Generation Open Access Ecosystem for Scientific Discovery Generated by AI Scientists, Pengsong Zhang et al., arXiv, 2025

• GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis, Haoyang Liu et al., arXiv, 2025

• AI Mathematician: Towards Fully Automated Frontier Mathematical Research, Yuanhang Liu et al., arXiv, 2025

• NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification, Bo Zhang et al., arXiv, 2025

• Large language models for scientific discovery in molecular property prediction, Yizhen Zheng et al., Nature Machine Intelligence, 2025

• Agent Laboratory: Using LLM Agents as Research Assistants, Samuel Schmidgall et al., arXiv, 2025

• AIDE: AI-Driven Exploration in the Space of Code, Zhengyao Jiang et al., arXiv, 2025

• SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning, Alireza Ghafarollahi et al., arXiv, 2024

• Empowering Biomedical Discovery with AI Agents, Shanghua Gao et al., arXiv, 2024

• Intelligent software for laboratory automation, Ken E. Whelan et al., Trends in Biotechnology, 2004

Physical, Robot, Experimentation

• Design of white circularly polarized luminescence with high g_lum across entire visible regions by dual-loop active learning, Peng Yang et al., Nature Communications, 2026

• AI-driven robotics for optics, Shiekh Zia Uddin et al., Science Advances, 2026

• Data-driven catalyst design for direct catalytic N2O decomposition, Chenxi He et al., Nature Communications, 2026

• On-demand growth of semiconductor heterostructures guided by physics-informed machine learning, Chao Shen et al., Science Advances, 2026

• Machine learning-assisted development of a fast Mechanochemical Johnson–Corey–Chaykovsky reaction, Francesco Mele et al., Nature Communications, 2026

• Hyperspace exploration using robotics for the discovery of mechanistically distinct transformations and complex functional products, Daniel Matuszczyk et al., Nature Synthesis, 2026

• SmartTrap: automated precision experiments with optical tweezers, Martin Selin et al., Nature Methods, 2026

• Timed batch inputs unlock substantially higher yields for enzymatic cascades, Miglė Jakštaitė et al., Nature Chemistry, 2026

• Accelerated discovery of highly stable ruthenium-based high-entropy oxides for acidic oxygen evolution, Yuanhua Tu et al., Science Advances, 2026

• Accelerated drug development using a digital formulator and a self-driving tableting data factory, Faisal Abbas et al., Nature Communications, 2026

• Deep active learning and knowledge transfer for rapid discovery of lithium metal battery electrolytes, Xufeng Hong et al., Nature Communications, 2026

• Active learning in latent spaces enables rapid inverse design of ferroelectric ceramics for energy storage, Zhaochen Xi et al., Nature Communications, 2026

• Data-driven intelligent carbonization unifies diverse biomass into high-performance hard carbon negative electrodes, Junfeng Cui et al., Nature Communications, 2026

• Synthetic data-driven deep learning for label-free autonomous atomic force microscopy, Ruben Millan-Solsona et al., Nature Communications, 2026

• Machine learning guided resolution of mechanical trade-off in polymer composites via stress adaptive interface, Hao Wang et al., Nature Communications, 2026

• YORU: Animal behavior detection with object-based approach for real-time closed-loop feedback, Hayato M. Yamanouchi et al., Science Advances, 2026

• Deep learning drives autonomous molecular reactions with single-bond selectivity in tetra-brominated porphyrins on Au(111), Zhiwen Zhu et al., Nature Communications, 2026

• Iterative discovery of potent polymeric antibiotics via multi-stage and multi-task learning against antimicrobial resistance, Yuhui Wu et al., Nature Communications, 2026

• MATTERIX: toward a digital twin for robotics-assisted chemistry laboratory automation, Kourosh Darvish et al., Nature Computational Science, 2026

• Adaptive AI decision interface for autonomous electronic material discovery, Yahao Dai et al., Nature Chemical Engineering, 2025

• Automation and machine learning drive rapid optimization of isoprenol production in Pseudomonas putida, David N. Carruthers et al., Nature Communications, 2025

• Self-driving lab discovers principles for steering spontaneous emission beyond conventional Fourier optics, Saaketh Desai et al., Nature Communications, 2026

• Heuristic data-driven approach for synergistic cobalt(IV)–enamine catalysis, Liang Cheng et al., Nature Synthesis, 2026

• Algorithmic iterative reticular synthesis of zeolitic imidazolate framework crystals, Zichao Rong et al., Nature Synthesis, 2026

• A software platform for real-time and adaptive neuroscience experiments, Anne Draelos et al., Nature Communications, 2025

• Discovery of highly fluorescent covalent organic frameworks through AI-assisted iterative experiment–learning cycles, Liang Zhang et al., Nature Chemistry, 2025

• Automated navigation of condensate phase behavior with active machine learning, Yannick H. A. Leurs et al., Nature Communications, 2025

• Active learning framework leveraging transcriptomics identifies modulators of disease phenotypes, Benjamin DeMeo et al., Science, 2025

• Evaluating large language model agents for automation of atomic force microscopy, Indrajeet Mandal et al., Nature Communications, 2025

• Reac-Discovery: an artificial intelligence–driven platform for continuous-flow catalytic reactor discovery and optimization, Cristopher Tinajero et al., Nature Communications, 2025

• Interpretable self-driving sputtering epitaxy reveals human-usable growth rules for β-Ga2O3 films, Yuki K. Wakabayashi et al., Nature Communications, 2026

• Rank-guided learning accelerates automated enzyme engineering, Jingyi Xu et al., Nature Communications, 2026

• An agentic artificially intelligent X-ray scientist, Zhantao Chen et al., Nature Machine Intelligence, 2026

• An autonomous lab for data-driven homogeneous catalysis, J. A. Bennett et al., Nature Communications, 2026

• Autonomous microfluidic experimentation for exploring reaction inference and synthesizing double perovskite nanoplatelets, Junbin Li et al., Nature Communications, 2026

• A flexible and affordable self-driving laboratory for automated reaction optimization, Simone Pilon et al., Nature Synthesis, 2026

• Experimental mechanician for plate lattice metamaterial discovery, Songtao Hu et al., Nature Communications, 2026

• Discovery of tunable and soluble organic emitters for solid-state lasers with a self-driving laboratory, Hyun Suk Park et al., Nature Communications, 2026

• Augmenting large language models with chemistry tools, Andres M. Bran et al., Nature Machine Intelligence, 2024

• ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization, Kourosh Darvish et al., Matter, 2024

• MatPilot: an LLM-enabled AI Materials Scientist under the Framework of Human-Machine Collaboration, Ziqi Ni et al., arXiv, 2024

• Autonomous mobile robots for exploratory synthetic chemistry, Tianwei Dai et al., Nature, 2024

• A multi-agent-driven robotic AI chemist enabling autonomous chemical research on demand, Tao Song et al., Chemrxiv, 2024

• Autonomous chemical research with large language models, Daniil A. Boiko et al., Nature, 2023

• An ontology for a Robot Scientist, Larisa N. Soldatova et al., Bioinformatics, 2006

Manuscript

• CiteSee: Augmenting Citations in Scientific Papers with Persistent and Personalized Historical Context, Joseph Chee Chang et al., arXiv, 2023

• Beyond Summarization: Designing AI Support for Real-World Expository Writing Tasks, Zejiang Shen et al., arXiv, 2023

• ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations, Yubo Wang et al., arXiv, 2025

Peer Review

• A large-scale randomized study of large language model feedback in peer review, Nitya Thakkar et al., Nature Machine Intelligence, 2026

• Automated scholarly paper review: Concepts, technologies, and challenges, Jialiang Lin et al., Information Fusion, 2023

• Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis, Jianxiang Yu et al., arXiv, 2024

• MARG: Multi-Agent Review Generation for Scientific Papers, Mike D'Arcy et al., arXiv, 2024

• Project Rachel: Can an AI Become a Scholarly Author?, arXiv 2511.14819, 2025.

Survey

• Towards self-driving laboratories in the biopharmaceutical industry, Samagra Dvivedi et al., Nature Synthesis, 2026

• Roadmap for transforming heterogeneous catalysis with artificial intelligence, Hongliang Xin et al., Nature Catalysis, 2026

• Artificial intelligence agents in cancer research and oncology, Daniel Truhn et al., Nature Reviews Cancer, 2026

• Autonomous catalysis research with human–AI–robot collaboration, Negin Orouji et al., Nature Catalysis, 2025

• The past, present and future of self-driving laboratories, Richard B. Canty, Milad Abolhasani, Nature Reviews Chemistry, 2026

• Agentic AI and the rise of in silico team science in biomedical research, Binglan Li et al., Nature Biotechnology, 2026

• What's Missing in Autonomous Research? A Systematization of Systems, Benchmarks, and Verification, Xingyu Ren et al., ResearchGate, 2026

• Synergy of robotics and microfluidics for intelligent micro-and nanomanipulation, Mengmeng Xi, Pengsong Zhang et al., Biomicrofluidics, 2025

• Large Language Models in Drug Discovery and Development: From Disease Mechanisms to Clinical Trials, Yizhen Zheng et al., arXiv, 2024

• Towards Scientific Discovery with Generative AI: Progress, Opportunities, and Challenges, Chandan K Reddy et al., arXiv, 2024

• Bridging AI and Science: Implications from a Large-Scale Literature Analysis of AI4Science, Yutong Xie et al., arXiv, 2024

• Paradigm shifts from data-intensive science to robot scientists, Xin Li et al., Science Bulletin, 2024

• A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery, Yu Zhang et al., arXiv, 2024

• Artificial Intelligence, Scientific Discovery, and Product Innovation, Toner-Rodgers Aidan, aidantr.github.io, 2024

• AI for Science: AI enabled scientific facility transforms fundamental research, Xiaokang Yang, Bulletin of Chinese Academy of Sciences, 2024

• Towards robot scientists for autonomous scientific discovery, Andrew Sparkes et al., Automated experimentation, 2010

News

• Accelerating Discovery in Natural Science Laboratories with AI and Robotics: Perspectives and Challenges from the 2024 IEEE ICRA Workshop, Yokohama, Japan, Andrew I. Cooper et al., IEEE ICRA Workshop, 2024

• A new golden age of discovery, Conor Griffin et al., Google DeepMind, 2024

• Transforming science labs into automated factories of discovery, Angelos Angelopoulos, Science Robotics, 2024

• Researchers built an ‘AI Scientist’ — what can it do?, Davide Castelvecchi et al., Nature, 2024

• How to Enter the Chen Institute & Science Prize for AI Accelerated Research, ChenSciencePrize@aaas.org et al., Science, 2024

• Advancing scientific discovery with the aid of robotics, Amos Matsiko, Science Robotics, 2024

Benchmark

• Evaluating LLMs' divergent thinking capabilities for scientific idea generation with minimal context, Kai Ruan et al., Nature Communications, 2026

• Benchmarking large language models on safety risks in scientific laboratories, Yujun Zhou et al., Nature Machine Intelligence, 2026

• Assessing AI's cognitive abilities for scientific discovery in the field of systems vaccinology, Lucie Rodriguez-Coffinet et al., Science Immunology, 2025

• AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era, Yunxiang Mo et al., arXiv, 2026

• MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI, Bohan Lyu et al., arXiv, 2026

• REFUTE: Scientific Critique & Epistemic Calibration Benchmark — Apache-2.0 Hugging Face benchmark for calibrated critique of recent science paper summaries. Technical report

• GenoTEX: An LLM Agent Benchmark for Automated Gene Expression Data Analysis, Haoyang Liu et al., MLCB, 2025

• CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark, Zachary S. Siegel et al., arXiv, 2024

• CiteBench: A benchmark for Scientific Citation Text Generation, Martin Funkquist et al., Conference on Empirical Methods in Natural Language Processing, 2022

Timeline

This timeline illustrates key milestones and future predictions in the development of autonomous AI Scientist and Robot Scientist.

Discussions

We love connecting with the community to discuss AI and Robot Scientist research, share insights, and collaborate on groundbreaking ideas! Join us on the following platforms:

• Slack: Connect with us on Slack for professional conversations, paper discussions, and networking with the AI research community.
  Join Slack

• WeChat Group: Join our WeChat group to discuss papers, share updates, and collaborate. Contact an admin (pengsong dot zhang@mail.utoronto.ca) to join.

We’re excited to hear your thoughts and contributions in our community!

Contributing

We welcome contributions to make this repository a richer resource for the AI and Robot Scientist community! To contribute:

1. Add Papers: Suggest new papers by submitting a pull request with the paper’s title, authors, link, and publication details in the appropriate section.
2. Enhance Content: Propose improvements to categories, summaries, or timelines.
3. Report Issues: Open an issue for typos, broken links, or suggestions.

Cite

bibtex
@article{zhang2025scaling,
  title={Scaling Laws in Scientific Discovery with AI and Robot Scientists},
  author={Zhang, Pengsong and Zhang, Heng and Xu, Huazhe and Xu, Renjun and Wang, Zhenting and Wang, Cong and Garg, Animesh and Li, Zhibin and Ajoudani, Arash and Liu, Xinyu},
  journal={arXiv preprint arXiv:2503.22444},
  year={2025}
}

@article{zhangautonomous,
  title={Autonomous Generalist Scientist: Towards and Beyond Human-Level Scientific Research with Agentic and Embodied AI and Robots},
  author={Zhang, Pengsong and Zhang, Heng and Xu, Huazhe and Xu, Renjun and Wang, Zhenting and Wang, Cong and Garg, Animesh and Li, Zhibin and Liu, Xinyu and Ajoudani, Arash},
  journal={ResearchGate preprint RG.2.2.35148.01923},
  year={2024}  
}

License

MIT