If you find this project helpful in your research, please consider cite:

@article{wei2025ai,
  title={From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery},
  author={Wei, Jiaqi and Yang, Yuejin and Zhang, Xiang and Chen, Yuhan and Zhuang, Xiang and Gao, Zhangyang and Zhou, Dongzhan and Wang, Guangshuai and Gao, Zhiqiang and Cao, Juntai and others},
  journal={arXiv preprint arXiv:2508.14111},
  year={2025}
}

In addition, "Awesome-Scientific-Datasets-and-LLMs" highlights the latest advances of scientific datasets and LLMs, which nicely complements our work.

@misc{hu2025surveyscientificlargelanguage,
      title={A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers}, 
      author={Ming Hu and Chenglong Ma and Wei Li and Wanghan Xu and Jiamin Wu and Jucheng Hu and Tianbin Li and Guohang Zhuang and Jiaqi Liu and Yingzhou Lu and Ying Chen and Chaoyang Zhang and Cheng Tan and Jie Ying and Guocheng Wu and Shujian Gao and Pengcheng Chen and Jiashi Lin and Haitao Wu and Lulu Chen and Fengxiang Wang and Yuanyuan Zhang and Xiangyu Zhao and Feilong Tang and Encheng Su and Junzhi Ning and Xinyao Liu and Ye Du and Changkai Ji and Cheng Tang and Huihui Xu and Ziyang Chen and Ziyan Huang and Jiyao Liu and Pengfei Jiang and Yizhou Wang and Chen Tang and Jianyu Wu and Yuchen Ren and Siyuan Yan and Zhonghua Wang and Zhongxing Xu and Shiyan Su and Shangquan Sun and Runkai Zhao and Zhisheng Zhang and Yu Liu and Fudi Wang and Yuanfeng Ji and Yanzhou Su and Hongming Shan and Chunmei Feng and Jiahao Xu and Jiangtao Yan and Wenhao Tang and Diping Song and Lihao Liu and Yanyan Huang and Lequan Yu and Bin Fu and Shujun Wang and Xiaomeng Li and Xiaowei Hu and Yun Gu and Ben Fei and Zhongying Deng and Benyou Wang and Yuewen Cao and Minjie Shen and Haodong Duan and Jie Xu and Yirong Chen and Fang Yan and Hongxia Hao and Jielan Li and Jiajun Du and Yanbo Wang and Imran Razzak and Chi Zhang and Lijun Wu and Conghui He and Zhaohui Lu and Jinhai Huang and Yihao Liu and Fenghua Ling and Yuqiang Li and Aoran Wang and Qihao Zheng and Nanqing Dong and Tianfan Fu and Dongzhan Zhou and Yan Lu and Wenlong Zhang and Jin Ye and Jianfei Cai and Wanli Ouyang and Yu Qiao and Zongyuan Ge and Shixiang Tang and Junjun He and Chunfeng Song and Lei Bai and Bowen Zhou},
      year={2025},
      eprint={2508.21148},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.21148}, 
}

Scientific discovery is experiencing a transformative shift, driven by the rapid evolution of artificial intelligence (AI) from specialized tools to collaborative research partners. This progression marks a pivotal stage in the AI for Science paradigm, where AI systems have moved from acting as computational oracles for targeted tasks toward the emergence of Agentic Science. In this stage, AI operates as an autonomous scientific agent capable of formulating hypotheses, designing and executing experiments, interpreting results, and iteratively refining theories with reduced dependence on human guidance.

Figure 1: Caption describing the main areas.

Despite significant progress, a unified framework for understanding and designing increasingly autonomous scientific systems is still lacking. While existing work has laid valuable foundations, it remains fragmented—focusing separately on workflows, autonomy scales, or architectures, and often lacking a clear emphasis on the natural sciences. To bridge these gaps, our work integrates and extends these perspectives through a comprehensive framework. Additionally, we present the first domain-oriented review of autonomous scientific discovery, offering a detailed synthesis of research advancements and key discoveries within each discipline.

Figure 2: Caption describing the main areas.

Finally, Our Key Contributions are as follows:

1. The Anatomy of Scientific Agents: Five Core Capabilities:

   • Reasoning and Planning
   • Tool Use and Integration
   • Memory Mechanisms
   • Multi-Agent Collaboration
   • Optimization and Evolution

2. The Dynamic Workflow of Agentic Science: Four Core Stages

   • Observation and Hypothesis Generation
   • Experimental Planning and Execution
   • Data Interpretation and Analysis:
   • Synthesis and Iterative Refinements.

3. Systematic Review Across Natural Sciences We conduct a comprehensive review of agentic systems across the major domains of natural science:

   • Life Sciences, Chemistry, Materials Science, and Physics.

• Part 0: Fully Autonomous Research Pipeline

• Part 1: Agentic Life Science Research

  • General Frameworks and Methodologies
  • Genomics, Transcriptomics and Multi-Omics Analysis
  • Protein Science and Engineering
  • Drug and Therapeutic Discovery

• Part 2: Agentic Chemistry Research

  • General Frameworks and Methodologies
  • Organic Synthesis and Reaction Optimization
  • Generative Chemistry and Molecular Design
  • Computational and Quantum Chemistry

• Part 3: Agentic Materials Science Research

  • General Frameworks and Automated Workflows
  • Structural and Functional Materials
  • Advanced and Quantum Materials

• Part 4: Agentic Physics and Astronomy Research

  • General Frameworks and Methodologies
  • Astronomy and Cosmology
  • Computational Mechanics and Fluid Dynamics
  • Quantum Computing

  ---

• SciMaster: Towards General-Purpose Scientific AI Agents, Part I. X-Master as Foundation: Can We Lead on Humanity's Last Exam?, Jingyi Chai et al.
• NovelSeek: When Agent Becomes the Scientist--Building Closed-Loop System from Hypothesis to Verification, Bo Zhang et al.
• Large language models for automated open-domain scientific hypotheses discovery, Zonglin Yang et al.
• Maps: A multi-agent framework based on big seven personality and socratic guidance for multimodal scientific problem solving, Jian Zhang et al.
• Agentrxiv: Towards collaborative autonomous research, Samuel Schmidgall et al.
• aiXiv: A Next-Generation Open-Access Platform for AI-Generated Research, Pengsong Zhang et al.
• Dolphin: Closed-loop open-ended auto-research through thinking, practice, and feedback, Jiakang Yuan et al.
• Towards an AI co-scientist, Juraj Gottweis et al.
• The AI scientist: Towards fully automated open-ended scientific discovery, Chris Lu et al.
• The virtual lab: AI agents design new SARS-CoV-2 nanobodies with experimental validation, Kyle Swanson et al.
• SpatialAgent: An autonomous AI agent for spatial biology, Hanchen Wang et al.
• Biomni: A general-purpose biomedical AI agent, Kexin Huang et al.
• Automating exploratory proteomics research via language models, Ning Ding et al.
• Matpilot: An LLM-enabled AI materials scientist under the framework of human-machine collaboration, Ziqi Ni et al.
• Tora: A tool-integrated reasoning agent for mathematical problem solving, Zhibin Gou et al.
• STELLA: Self-Evolving LLM Agent for Biomedical Research, Ruofan Jin et al.
• Two heads are better than one: A multi-agent system has the potential to improve scientific idea generation, Haoyang Su et al.
• Dora AI scientist: Multi-agent virtual research team for scientific exploration discovery and automated report generation, Vladimir Naumov et al.
• DiscoveryWorld: A virtual environment for developing and evaluating automated scientific discovery agents, Peter Jansen et al.
• Autonomous chemical research with large language models, Daniil A. Boiko et al.
• ResearchAgent: Iterative research idea generation over scientific literature with large language models, Jinheon Baek et al.
• Agent laboratory: Using LLM agents as research assistants, Samuel Schmidgall et al.
• Agent hospital: A simulacrum of hospital with evolvable medical agents, Junkai Li et al.
• Conversational health agents: A personalized LLM-powered agent framework, Mahyar Abbasian et al.
• An automatic end-to-end chemical synthesis development platform powered by large language models, Yixiang Ruan et al.
• AlphaEvolve: A coding agent for scientific and algorithmic discovery, Alexander Novikov et al.
• Accelerated end-to-end chemical synthesis development with large language models, Yixiang Ruan et al.
• DeepAnalyze: Agentic Large Language Models for Autonomous Data Science, Shaolei Zhang et al.

• Biomni: A General-Purpose Biomedical AI Agent, Kexin Huang et al.
• m-KAILIN: A Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training, Meng Xiao et al.
• STELLA: Self-Evolving LLM Agent for Biomedical Research, Ruofan Jin et al.
• From Intention to Implementation: Automating Biomedical Research via LLMs, Yi Luo et al.
• PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration, Yingming Pu et al.
• Empowering Biomedical Discovery with AI Agents, Shanghua Gao et al.

• GeneAgent: Self-verification Language Agent for Gene Set Knowledge Discovery using Domain Databases, Zhizheng Wang et al.
• BioInformatics Agent (BIA): Unleashing the Power of Large Language Models to Reshape Bioinformatics Workflow, Qi Xin et al.
• CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis, Yihang Xiao et al.
• Toward a Team of AI-Made Scientists for Scientific Discovery from Gene Expression Data, Haoyang Liu et al.
• GenoTEX: An LLM Agent Benchmark for Automated Gene Expression Data Analysis, Haoyang Liu et al.
• GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis, Haoyang Liu et al.
• CRISPR-GPT: An LLM Agent for Automated Design of Gene-Editing Experiments, Kaixuan Huang et al.
• SpatialAgent: An Autonomous AI Agent for Spatial Biology, Hanchen Wang et al.
• PhenoGraph: A Multi-Agent Framework for Phenotype-Driven Discovery in Spatial Transcriptomics Data Augmented with Knowledge Graphs, Seyednami Niyakan et al.
• BioAgents: Democratizing Bioinformatics Analysis with Multi-Agent Systems, Nikita Mehandru et al.
• BioMaster: Multi-Agent System for Automated Bioinformatics Analysis Workflow, Houcheng Su et al.
• TransAgent: Dynamizing Transcriptional Regulation Analysis via Multi-Omics-Aware AI Agent, Guorui Zhang et al.
• CompBioAgent: An LLM-Powered Agent for Single-Cell RNA-Seq Data Exploration, Haotian Zhang et al.
• PerTurboAgent: A Self-Planning Agent for Boosting Sequential Perturb-seq Experiments, Minsheng Hao et al.
• PROTEUS: Automating Exploratory Multiomics Research via Language Models, Ning Ding et al.
• CellVoyager: AI CompBio Agent Generates New Insights by Autonomously Analyzing Biological Data, Samuel Alber et al.
• AstroAgents: A Multi-Agent AI for Hypothesis Generation from Mass Spectrometry Data, Daniel Saeedi et al.
• BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments, Yusuf Roohani et al.

• ProtAgents: Protein Discovery via Large Language Model Multi-Agent Collaborations Combining Physics and Machine Learning, Alireza Ghafarollahi et al.
• Sparks: Multi-Agent Artificial Intelligence Model Discovers Protein Design Principles, Alireza Ghafarollahi et al.

• The Virtual Lab: AI Agents Design New SARS-CoV-2 Nanobodies with Experimental Validation, Kyle Swanson et al.
• OriGene: A Self-Evolving Virtual Disease Biologist Automating Therapeutic Target Discovery, Zhongyue Zhang et al.
• Large Language Model Agent for Modular Task Execution in Drug Discovery, Janghoon Ock et al.
• TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools, Shanghua Gao et al.
• Robin: A Multi-Agent System for Automating Scientific Discovery, Ali Essam Ghareeb et al.
• DrugAgent: Automating AI-Aided Drug Discovery Programming Through LLM Multi-Agent Collaboration, Sizhe Liu et al.
• LIDDIA: Language-Based Intelligent Drug Discovery Agent, Reza Averly et al.
• PharmAgents: Building a Virtual Pharma with Large Language Model Agents, Bowen Gao et al.
• CLADD: RAG-Enhanced Collaborative LLM Agents for Drug Discovery, Namkyeong Lee et al.
• Tippy: Accelerating Drug Discovery Through Agentic AI, Yao Fehlis et al.
• ACEGEN: Reinforcement Learning of Generative Chemical Agents for Drug Discovery, Albert Bou et al.
• Exploring Modularity of Agentic Systems for Drug Discovery, Laura van Weesep et al.
• DO Challenge: Can AI Agents Design and Implement Drug Discovery Pipelines?, Khachik Smbatyan et al.

• ChemCrow: Augmenting large-language models with chemistry tools, Andres M. Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D. White, Philippe Schwaller.
• A multiagent-driven robotic AI chemist enabling autonomous chemical research on demand, Tao Song, Man Luo, Xiaolong Zhang, Linjiang Chen, Yan Huang, Jiaqi Cao, Qing Zhu, Daobin Liu, Baicheng Zhang, Gang Zou, et al.
• MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses, Zonglin Yang, Wanhao Liu, Ben Gao, Tong Xie, Yuqiang Li, Wanli Ouyang, Soujanya Poria, Erik Cambria, Dongzhan Zhou.
• MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback, Wanhao Liu, Zonglin Yang, Jue Wang, Lidong Bing, Di Zhang, Dongzhan Zhou, Yuqiang Li, Houqiang Li, Erik Cambria, Wanli Ouyang.
• An autonomous large language model agent for chemical literature data mining, Kexin Chen, Hanqun Cao, Junyou Li, Yuyang Du, Menghao Guo, Xin Zeng, Lanqing Li, Jiezhong Qiu, Pheng Ann Heng, Guangyong Chen.
• Agent-based learning of materials datasets from the scientific literature, Mehrad Ansari, Seyed Mohamad Moosavi.
• ChemAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning, Mengsong Wu, YaFei Wang, Yidong Ming, Yuqi An, Yuwei Wan, Wenliang Chen, Binbin Lin, Yuqiang Li, Tong Xie, Dongzhan Zhou.
• ChemHAS: Hierarchical Agent Stacking for Enhancing Chemistry Tools, Zhucong Li, Bowei Zhang, Jin Xiao, Zhijian Zhou, Fenglei Cao, Jiaqing Liang, Yuan Qi.
• ChemToolAgent: The impact of tools on language agents for chemistry problem solving, Botao Yu, Frazier N. Baker, Ziru Chen, Garrett Herb, Boyu Gou, Daniel Adu-Ampratwum, Xia Ning, Huan Sun.
• Chemagent: Self-updating library in large language models improves chemical reasoning, Xiangru Tang, Tianyu Hu, Muyang Ye, Yanjun Shao, Xunjian Yin, Siru Ouyang, Wangchunshu Zhou, Pan Lu, Zhuosheng Zhang, Yilun Zhao, et al.
• LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents, Rui Li, Zixuan Hu, Wenxi Qu, Jinouwen Zhang, Zhenfei Yin, Sha Zhang, Xuantuo Huang, Hanqing Wang, Tai Wang, Jiangmiao Pang, et al.
• Cactus: Chemistry agent connecting tool usage to science, Andrew D. McNaughton, Gautham Krishna Sankar Ramalaxmi, Agustin Kruel, Carter R. Knutson, Rohith A. Varikoti, Neeraj Kumar.
• AI agents in chemical research: GVIM--an intelligent research assistant system, Kangyong Ma.
• MT-Mol: Multi Agent System with Tool-based Reasoning for Molecular Optimization, Hyomin Kim, Yunhui Jang, Sungsoo Ahn.
• CSstep: Step-by-step exploration of the chemical space of drug molecules via multi-agent and multi-stage reinforcement learning, Xinhao Che, Yujing Zhao, Qilei Liu, Fang Yu, Hanyu Gao, Lei Zhang.
• Agentic Mixture-of-Workflows for Multi-Modal Chemical Search, Tiffany J. Callahan, Nathaniel H. Park, Sara Capponi.

• Autonomous chemical research with large language models, Daniil A. Boiko, Robert MacKnight, Ben Kline, Gabe Gomes.
• Accelerated end-to-end chemical synthesis development with large language models, Yixiang Ruan, Chenyin Lu, Ning Xu, Jian Zhang, Jun Xuan, Jianzhang Pan, Qun Fang, Hanyu Gao, Xiaodong Shen, Ning Ye, et al.
• Chemist-X: Large language model-empowered agent for reaction condition recommendation in chemical synthesis, Kexin Chen, Junyou Li, Kunyi Wang, Yuyang Du, Jiahui Yu, Jiamin Lu, Lanqing Li, Jiezhong Qiu, Jianzhang Pan, Yi Huang, et al.
• ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization, Kourosh Darvish, Marta Skreta, Yuchi Zhao, Naruki Yoshikawa, Sagnik Som, Miroslav Bogdanovic, Yang Cao, Han Hao, Haoping Xu, Alán Aspuru-Guzik, et al.
• Delocalized, asynchronous, closed-loop discovery of organic laser emitters, Felix Strieth-Kalthoff, Han Hao, Vandana Rathore, Joshua Derasp, Théophile Gaudin, Nicholas H. Angello, Martin Seifrid, Ekaterina Trushina, Mason Guy, Junliang Liu, et al.
• AutoChemSchematic AI: A Closed-Loop, Physics-Aware Agentic Framework for Auto-Generating Chemical Process and Instrumentation Diagrams, Sakhinana Sagar Srinivas, Shivam Gupta, Venkataramana Runkana.

• ChatMOF: An autonomous AI system for predicting and generating metal-organic frameworks, Yeonghun Kang, Jihan Kim.
• System of agentic AI for the discovery of metal-organic frameworks, Theo Jaffrelot Inizan, Sherry Yang, Aaron Kaplan, Yen-Hsu Lin, Jian Yin, Saber Mirzaei, Mona Abdelgaid, Ali H. Alawadhi, KwangHwan Cho, Zhiling Zheng, et al.
• OSDA Agent: Leveraging Large Language Models for De Novo Design of Organic Structure Directing Agents, Zhaolin Hu, Yixiao Zhou, Zhongan Wang, Xin Li, Weimin Yang, Hehe Fan, Yi Yang.
• ChemReasoner: Heuristic search over a large language model's knowledge space using quantum-chemical feedback, Henry W. Sprueill, Carl Edwards, Khushbu Agarwal, Mariefel V. Olarte, Udishnu Sanyal, Conrad Johnston, Hongbin Liu, Heng Ji, Sutanay Choudhury.
• Molecular design in synthetically accessible chemical space via deep reinforcement learning, Julien Horwood, Emmanuel Noutahi.

• El Agente: An autonomous agent for quantum chemistry, Yunheng Zou, Austin H. Cheng, Abdulrahman Aldossary, Jiaru Bai, Shi Xuan Leong, Jorge Arturo Campos-Gonzalez-Angulo, Changhyeok Choi, Cher Tian Ser, Gary Tom, Andrew Wang, et al.
• Aitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulations, Jinming Hu, Hassan Nawaz, Yuting Rui, Lijie Chi, Arif Ullah, Pavlo O. Dral.
• ChemGraph: An Agentic Framework for Computational Chemistry Workflows, Thang D. Pham, Aditya Tanikanti, Murat Keçeli.
• xchemagents: Agentic AI for explainable quantum chemistry, Can Polat, Mehmet Tuncel, Mustafa Kurban, Erchin Serpedin, Hasan Kurban.

• AILA: Autonomous microscopy experiments through large language model agents, Indrajeet Mandal, Jitendra Soni, Mohd Zaki, Morten M. Smedskjaer, Katrin Wondraczek, Lothar Wondraczek, Nitya Nand Gosvami, NM Krishnan.
• Foam-Agent: Towards Automated Intelligent CFD Workflows, Ling Yue, Nithin Somasekharan, Yadi Cao, Shaowu Pan.
• ChemGraph: An Agentic Framework for Computational Chemistry Workflows, Thang D. Pham, Aditya Tanikanti, Murat Keçeli.
• MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge, Bo Ni, Markus J. Buehler.
• MatPilot: An LLM-enabled AI materials scientist under the framework of human-machine collaboration, Ziqi Ni, Yahao Li, Kaijia Hu, Kunyuan Han, Ming Xu, Xingyu Chen, Fengqi Liu, Yicong Ye, Shuxin Bai.
• LLMatDesign: Autonomous materials discovery with large language models, Shuyi Jia, Chao Zhang, Victor Fung.
• MAPPS: Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists, Lianhao Zhou, Hongyi Ling, Keqiang Yan, Kaiji Zhao, Xiaoning Qian, Raymundo Arróyave, Xiaofeng Qian, Shuiwang Ji.
• LLaMP: Large language model made powerful for high-fidelity materials knowledge retrieval and distillation, Yuan Chiang, Elvis Hsieh, Chia-Hong Chou, Janosh Riebesell.
• HoneyComb: A flexible LLM-based agent system for materials science, Huan Zhang, Yu Song, Ziyu Hou, Santiago Miret, Bang Liu.
• Multicrossmodal Automated Agent for Integrating Diverse Materials Science Data, Adib Bazgir, Yuwen Zhang, et al.
• PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration, Yingming Pu, Tao Lin, Hongyu Chen.
• dZiner: Rational inverse design of materials with AI agents, Mehrad Ansari, Jeffrey Watchorn, Carla E. Brown, Joseph S. Brown.
• Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents, Shrinidhi Kumbhar, Venkatesh Mishra, Kevin Coutinho, Divij Handa, Ashif Iquebal, Chitta Baral.
• AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use, Yaotian Yang, Yiwen Tang, Yizhe Chen, Xiao Chen, Jiangjie Qiu, Hao Xiong, Haoyu Yin, Zhiyao Luo, Yifei Zhang, Sijia Tao, Wentao Li, Qinghua Zhang, Yuqiang Li, Wanli Ouyang, Bin Zhao, Xiaonan Wang, Fei Wei.

• AtomAgents: Alloy design and discovery through physics-aware multi-modal multi-agent artificial intelligence, Alireza Ghafarollahi, Markus J. Buehler.
• Automating alloy design and discovery with physics-aware multimodal multiagent AI, Alireza Ghafarollahi, Markus J. Buehler.
• Rapid and automated alloy design with graph neural network-powered LLM-driven multi-agent systems, Alireza Ghafarollahi, Markus J. Buehler.
• metaAgent: Electromagnetic metamaterial discovery through multi-agent collaboration, Jie Tian, Martin Taylor Sobczak, Dhanush Patil, Jixin Hou, Lin Pang, Arunachalam Ramanathan, Libin Yang, Xianyan Chen, Yuval Golan, Xiaoming Zhai, et al.
• CrossMatAgent: A Multi-Agent Framework for Accelerated Metamaterial Design, Jie Tian, Martin Taylor Sobczak, Dhanush Patil, et al.
• An Agentic Framework for Autonomous Metamaterial Modeling and Inverse Design, Darui Lu, Jordan M. Malof, Willie J. Padilla.

• SciAgents: Automating scientific discovery through bioinspired multi-agent intelligent graph reasoning, Alireza Ghafarollahi, Markus J. Buehler.
• PriM: Principle-inspired material discovery through multi-agent collaboration, Zheyuan Lai, Yingming Pu.
• TopoMAS: Large Language Model Driven Topological Materials Multiagent System, Baohua Zhang, Xin Li, Huangchao Xu, Zhong Jin, Quansheng Wu, Ce Li.

• MoRA: Improving physics reasoning in large language models using mixture of refinement agents, Raj Jaiswal, Dhruv Jain, Harsh Parimal Popat, Avinash Anand, Abhishek Dharmadhikari, Atharva Marathe, Rajiv Ratn Shah.
• LP-COMDA: Physics-informed LLM-agent for automated modulation design in power electronics systems, Junhua Liu, Fanfan Lin, Xinze Li, Kwan Hui Lim, Shuai Zhao.
• LLMSat: A large language model-based goal-oriented agent for autonomous space exploration, David Maranto.
• ArgoLOOM: Agentic AI for Fundamental Physics from Quarks to Cosmos, S. D. Bakshi, P. Barry, C. Bissolotti, I. Cloet, S. Corrodi, Z. Djurcic, S. Habib, K. Heitmann, T. J. Hobbs, W. Hopkins, S. Joosten, B. Kriesten, N. Ramachandran, A. Wells, M. Zurek.
• Agentic AI for Multi-Stage Physics Experiments at a Large-Scale User Facility Particle Accelerator, Thorsten Hellert, Drew Bertwistle, Simon C. Leemann, Antonin Sulc, Marco Venturini.
• CosmoAgent: What if LLMs have different world views: Simulating alien civilizations with LLM-based agents, Zhaoqian Xue, Beichen Wang, Suiyuan Zhu, Kai Mei, Hua Tang, Wenyue Hua, Mengnan Du, Yongfeng Zhang.

• StarWhisper: Agent-based observation assistant system to approach AI astrophysicist, Cunshi Wang, Xinjie Hu, Yu Zhang, Xunhao Chen, Pengliang Du, Yiming Mao, Rui Wang, Yuyang Li, Ying Wu, Hang Yang, et al.
• mephisto: Interpreting multi-band galaxy observations with large language model-based agents, Zechang Sun, Yuan-Sen Ting, Yaobo Liang, Nan Duan, Song Huang, Zheng Cai.
• AI Agents for ground-based gamma astronomy, Dmitriy Kostunin, Vladimir Sotnikov, Sergo Golovachev, Alexandre Strube.
• The AI Cosmologist I: An Agentic System for Automated Data Analysis, Adam Moss.
• SimAgents: Bridging Literature and the Universe Via A Multi-Agent Large Language Model System, Xiaowen Zhang, Zhenyu Bi, Xuan Wang, Tiziana Di Matteo, Rupert A.C. Croft.

• OpenFOAMGPT: A RAG-augmented LLM agent for OpenFOAM-based computational fluid dynamics, Sandeep Pandey, Ran Xu, Wenkang Wang, Xu Chu.
• OpenFOAMGPT 2.0: End-to-end, trustworthy automation for computational fluid dynamics, Jingsen Feng, Ran Xu, Xu Chu.
• LLM-Agent: A Large Language Model-Empowered Agent for Reliable and Robust Structural Analysis, Jiachen Liu, Ziheng Geng, Ran Cao, Lu Cheng, Paolo Bocchini, Minghui Cheng.
• MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge, Bo Ni, Markus J. Buehler.
• AutoGen-FEM: Optimizing Collaboration of Large Language Model Based Agents for Autonomous Finite Element Analysis, Chuan Tian, et al.

• k-agents: Agents for self-driving laboratories applied to quantum computing, Shuxiang Cao, Zijian Zhang, Mohammed Alghadeer, Simone D. Fasciati, Michele Piscitelli, Mustafa Bakr, Peter Leek, Alán Aspuru-Guzik.

Contributions are highly encouraged!

If you have a relevant paper that complements this taxonomy, feel free to submit a pull request or reach out to the author directly.

Your support will help expand and improve this repository!