AI agents for scientific discovery: papers, tools, and an interactive bilingual atlas with detailed reading guides.
See the codeA curated list of papers, tools, and platforms on AI agents for scientific discovery (2023–2026) — spanning general science copilots, self-evolving agents and continual learning, benchmarks, physical sciences, life sciences, and social-science simulation.
Click any paper to understand what it does. Explore the collection on a timeline, then open a detailed reading guide with method steps, experimental results, original figures and tables, takeaways, authors, and institutions. Search by research question, author, or institution, and combine discipline and mechanism filters. No installation or sign-in needed.
推荐打开交互网页阅读: 在时间图谱中点击任意论文,查看具体方法、实验结果、原图表导读、主要结论及作者机构;支持中英切换、搜索和组合筛选。
Click the preview to explore the live atlas. 点击预览图,打开交互网页。
Quick links: Self-evolving agents & continual learning · Paper list · Reading and maintenance guide.
We're continually improving and expanding this collection. To add a paper, please see CONTRIBUTING.md or open an issue. For other inquiries: zoedusy123@gmail.com.
Type tags (blue):
Domain tags (green):
See CONTRIBUTING.md for tag definitions.
🌐 Cross-domain agentic systems, AI scientists, and research copilots.
[2026-07]
"Jacobian: Composable mathematics for agent-driven research experiments." code | project
[2026-06]
"Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy." Youran Sun et al. arXiv 2026. paper | code
[2026-06] "What's Missing in Autonomous Research? A Systematization of Systems, Benchmarks, and Verification." Xingyu Ren et al. Technical report 2026. paper
[2026-01] "Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts." Dhruv Trehan and Paras Chopra. arXiv 2026. paper
[2025-11]
"Kosmos: An AI Scientist for Autonomous Discovery." Ludovico Mitchener et al. (FutureHouse / Edison Scientific). arXiv 2025. paper | platform
[2025-10] "Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics." arXiv 2025. paper
[2025-08] "From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery." arXiv 2025. paper
[2025-04]
"The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search." Yutaro Yamada et al. arXiv 2025. paper | code
[2025-03] "AgentRxiv: Towards Collaborative Autonomous Research." Samuel Schmidgall and Michael Moor. arXiv 2025. paper | project
[2025-02] "Towards an AI co-scientist." Juraj Gottweis et al. (Google). arXiv 2025. paper | blog
[2025-01]
"Agent Laboratory: Using LLM Agents as Research Assistants." Samuel Schmidgall et al. EMNLP Findings 2025. paper | code
[2024-08] "MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents." Ruochen Li et al. arXiv 2024. paper | code
[2024-08]
"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery." Chris Lu et al. arXiv 2024. paper | code
[2024-06]
"AutoSurvey: Large Language Models Can Automatically Write Surveys." Yidong Wang et al. NeurIPS 2024. paper | code
[2023-12] "PaperQA: Retrieval-augmented generative agent for scientific research." Jakub Lála et al. arXiv 2023. paper
[2023-06] "Scientific discovery in the age of artificial intelligence." Hanchen Wang et al. Nature 2023. paper
🔄 Scientific agents that retain experience, acquire skills, adapt model parameters, or improve their own research machinery. Selected RSI (recursive self-improvement) foundations are included for their relevance to building and evaluating scientific agents.
Explore this topic in the interactive atlas → — compare papers on the timeline and open their detailed reading guides.
See the reading guide for mechanisms, scientific applications, evidence limits, and domain-specific works. Literature checked through 2026-09-12; entry dates refer to first publication, not the latest revision.
[2026-08]
"HypoForge: A Self-Improving Multi-Agent Framework for Automated Hypothesis Generation and Testing via Scientific Skill Learning." Ziqing Qian et al. arXiv 2026. paper
[2026-08] "Meta$^n$: Recursive Self-Improvement through Emergent Depth." Zae Myung Kim et al. arXiv 2026. paper | code
[2026-07] "SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition." Yuqi Tang et al. arXiv 2026. paper
[2026-06] "Evidence-Informed LLM Beliefs for Continual Scientific Discovery." Dhruv Agarwal et al. arXiv 2026. paper
[2026-06]
"MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery." Shangheng Du et al. arXiv 2026. paper | code
[2026-04] "EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale." Xinyu Zhu et al. arXiv 2026. paper | code
[2026-04]
"CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery." Ao Qu et al. COLM 2026. paper | code
[2026-03]
"Hyperagents." Jenny Zhang et al. arXiv 2026. paper | code
[2026-03]
"EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery." Yougang Lyu et al. arXiv 2026. paper | code
[2026-02]
"S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research." S1-NexusAgent Team. arXiv 2026. paper | code
[2026-01]
"Learning to Discover at Test Time." Mert Yuksekgonul et al. arXiv 2026. paper | code
[2025-05] "AlphaEvolve: A coding agent for scientific and algorithmic discovery." Alexander Novikov et al. arXiv 2025. paper | blog
[2025-05] "Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents." Jenny Zhang et al. arXiv 2025. paper | code
📊 Datasets, leaderboards, and evaluation frameworks.
[2026-08] "AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement." Yizhe Chi et al. arXiv 2026. paper
[2026-03] "ResearchClawBench" (code-only release). code | website
[2025-12] "Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows (SGI-Bench)." Wanghan Xu et al. (Shanghai AI Lab). arXiv 2025. paper | code | website
[2025-05] "MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research." Hui Chen et al. NeurIPS 2025 Datasets and Benchmarks Track. paper
[2025-05]
"AI-Researcher: Autonomous Scientific Innovation." HKUDS et al. arXiv 2025. paper
[2025-04] "PaperBench: Evaluating AI's Ability to Replicate AI Research." Giulio Starace et al. arXiv 2025. paper
[2024-10] "MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering." Jun Shern Chan et al. ICLR 2025. paper
[2024-10] "ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery." Ziru Chen et al. ICLR 2025. paper
⚛️ Physics · Chemistry · Earth Sciences · Astronomy · Materials.
[2026-08]
"AgentFEM: An AI-Native Open-Source Platform for Finite-Element Computing." Haoming Luo. Technical report 2026. paper | code | project
[2026-07]
"Harnessing agent memory to build lifelong AI partners for materials scientists." Siyu Liu et al. arXiv 2026. paper
[2026-06]
"Self-Evolving Scientific Agent Designs Physically Reasoned White-Box Fluid Control." Boai Sun et al. arXiv 2026. paper | code
[2026-05]
"GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms." Juan Diego Toscano, Zhaojie Chai, and George Em Karniadakis. arXiv 2026. paper
[2026-02]
"AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing." Jianda Du, Youran Sun, and Haizhao Yang. arXiv 2026. paper | code
[2026-02]
"Knowledge-driven autonomous materials research via collaborative multi-agent and robotic system (MARS)." Tongyu Shi et al. Matter 2026. paper
[2025-12]
"CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution." Xu Huang et al. arXiv 2025. paper
[2025-12]
"An Agentic Framework for Autonomous Materials Computation." arXiv 2025. paper
[2025-12]
"Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Functional Materials Discovery." arXiv 2025. paper
[2025-08] "SciToolAgent: A knowledge-graph-driven scientific agent for multitool integration." Nature Computational Science 2025. paper
[2025-06]
"CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning." arXiv 2025. paper | code
[2025-04]
"MOFGen: System of Agentic AI for the Discovery of Metal-Organic Frameworks." Théo Jaffrelot Inizan et al. (UC Berkeley / Google DeepMind). arXiv 2025. paper
[2025-04]
"PriM: Principle-Inspired Material Discovery through Multi-Agent Collaboration." arXiv 2025. paper
[2024-12]
"SciAgents: Automating Scientific Discovery Through Bioinspired Multi-Agent Intelligent Graph Reasoning." Alireza Ghafarollahi and Markus J. Buehler. Advanced Materials 2025. paper | code
[2024-07]
"A Review of Large Language Models and Autonomous Agents in Chemistry." Mayk Caldas Ramos et al. arXiv 2024. paper
[2024-06]
"LLMatDesign: Autonomous Materials Discovery with Large Language Models." Shuyi Jia et al. arXiv 2024. paper
[2024-05]
"ChatMOF: An Artificial Intelligence System for Predicting and Generating Metal-Organic Frameworks Using Large Language Models." Yeonghun Kang and Jihan Kim. Nature Communications 2024. paper
[2023-12]
"Autonomous chemical research with large language models." Daniil A. Boiko et al. Nature 2023. paper
[2023-12]
"Augmenting large language models with chemistry tools (ChemCrow)." Andres M. Bran et al. Nature Machine Intelligence 2024. paper
🧬 Biology · Botany · Zoology · Microbiology · Neuroscience · Medicine.
[2026-09]
"ADMET-EvO: a self-evolving scientific agent for sustained research across heterogeneous tasks." Yiling Zhou et al. arXiv 2026. paper
[2026-04]
"An autonomous LLM-agent platform for computational binder design and conjugation-aware prioritization of antibody–drug conjugates." Ganggang Liu et al. bioRxiv 2026. paper | code
[2026-03] "Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents." Jacopo Teneggi et al. arXiv 2026. paper
[2026-03]
"Empowering AI data scientists using a multi-agent LLM framework with self-evolving capabilities for autonomous, tool-aware biomedical data analyses (BioMedAgent)." Dechao Bu et al. Nature Biomedical Engineering 2026. paper
[2026-02]
"A Multi-Agent Framework for Medical AI: Leveraging Fine-Tuned GPT, LLaMA, and DeepSeek R1 for Evidence-Based and Bias-Aware Clinical Query Processing." Naeimeh Nourmohammadi et al. arXiv 2026. paper
[2026-01]
"Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis." Hao Li et al. (Peking University). arXiv 2026. paper
[2026-01]
"Virtual lab of artificial intelligence agents accelerating nanobody design against SARS-CoV-2 variants." Hakjin Kim et al. International Journal of Biological Sciences 2026. paper
[2025-10]
"The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies." Kyle Swanson et al. Nature 2025. paper | code
[2025-07]
"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis." Haoyang Liu et al. arXiv 2025. paper
[2025-07]
"STELLA: Self-Evolving LLM Agent for Biomedical Research." Ruofan Jin et al. arXiv 2025. paper | code
[2025-05] "Robin: A multi-agent system for automating scientific discovery." Ali Essam Ghareeb et al. (FutureHouse). arXiv 2025. paper | blog
[2025-05] "Biomni: A General-Purpose Biomedical AI Agent." Kexin Huang et al. (Stanford). bioRxiv 2025. paper | platform
[2025-03]
"TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools." Shanghua Gao et al. (Harvard). arXiv 2025. paper | project | code
[2024-11]
"DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration." Sizhe Liu et al. arXiv 2024. paper
[2024-11] "TourSynbio-Agent: Validation of an LLM-based Multi-Agent Framework for Protein Engineering in Dry Lab and Wet Lab." Y. Shen et al. arXiv 2024. paper
[2024-10]
"An AI Agent for Fully Automated Multi-Omic Analyses." Juexiao Zhou et al. Advanced Science 2024. paper
[2024-10]
"BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments." Yusuf Roohani et al. arXiv 2024. paper
[2024-08]
"BioImage.IO Chatbot: a community-driven AI assistant for integrative computational bioimaging." Wanlu Lei et al. Nature Methods 2024. paper
[2024-08] "TourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineering." Y. Shen et al. arXiv 2024. paper
[2024-07]
"MMedAgent: Learning to Use Medical Tools with Multi-modal Agent." Binxu Li et al. arXiv 2024. paper
[2024-07]
"ClinicalAgent: Clinical Trial Multi-Agent System with Large Language Model-based Reasoning." Yue Ling et al. arXiv 2024. paper
[2024-07] "Empowering Biomedical Discovery with AI Agents." Shanghua Gao et al. arXiv 2024. paper
[2024-06]
"Omega — harnessing the power of large language models for bioimage analysis." Loïc A. Royer. Nature Methods 2024. paper
[2024-05]
"CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis." Yihang Xiao et al. bioRxiv 2024. paper
[2024-05]
"BioInformatics Agent (BIA): Unleashing the Power of Large Language Models to Reshape Bioinformatics Workflow." Qi Xin et al. bioRxiv 2024. paper
[2024-05]
"Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents." Junkai Li et al. arXiv 2024. paper
[2024-04]
"CRISPR-GPT: An LLM Agent for Automated Design of Gene-Editing Experiments." Kaixuan Huang et al. arXiv 2024. paper
[2024-02] "ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning." Alireza Ghafarollahi and Markus J. Buehler. Digital Discovery 2024. paper
[2024-02]
"A multimodal generative AI copilot for human pathology." Ming Y. Lu et al. Nature 2024. paper
[2023-12]
"De novo drug design using reinforcement learning with multiple GPT agents." Xiuyuan Hu et al. NeurIPS 2023. paper
[2023-11]
"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning." Xiangru Tang et al. arXiv 2023. paper
[2023-08]
"Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue." S. Yang et al. arXiv 2023. paper
[2023-07]
"Epidemic modeling with generative agents." Ross Williams et al. arXiv 2023. paper
[2023-05]
"HuatuoGPT: Towards Taming Language Model to Be a Doctor." H. Zhang et al. arXiv 2023. paper
[2023-03] "Biological research and self-driving labs in deep space supported by artificial intelligence." Lauren M. Sanders et al. Nature Machine Intelligence 2023. paper
👥 Economics · sociology · political science · generative-agent simulation.
[2024-04] "ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models." Jinheon Baek et al. arXiv 2024. paper
[2023-11]
"ALYMPICS: Language Agents Meet Game Theory." Shaoguang Mao et al. arXiv 2023. paper
[2023-10]
"Lyfe Agents: Generative agents for low-cost real-time social interactions." Zhao Kaiya et al. arXiv 2023. paper
[2023-10]
"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents." Xuhui Zhou et al. arXiv 2023. paper
[2023-10]
"Large Language Model-Empowered Agents for Simulating Macroeconomic Activities." Nian Li et al. arXiv 2023. paper
[2023-10] "Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View." Jintian Zhang et al. arXiv 2023. paper
[2023-07]
"S³: Social-network Simulation System with Large Language Model-Empowered Agents." Chen Gao et al. arXiv 2023. paper
[2023-07] "The SocialAI school: Insights from developmental psychology towards artificial socio-cultural agents." Grgur Kovač et al. arXiv 2023. paper
[2023-07]
"Understanding the benefits and challenges of using large language model-based conversational agents for mental well-being support." Zilin Ma et al. arXiv 2023. paper
[2023-04]
"Generative agents: Interactive simulacra of human behavior." Joon Sung Park et al. arXiv 2023. paper
[2023-01] "Large language models as simulated economic agents: What can we learn from homo silicus?" John J. Horton. National Bureau of Economic Research 2023. paper
Contributions are very welcome! Please read CONTRIBUTING.md before opening a PR. For paper suggestions you can also open an issue using the Paper Submission template.
This list is released under CC0 1.0 Universal — to the extent possible under law, the maintainers have waived all copyright and related rights to this work. Underlying papers, code, and platforms remain under their respective licenses.
Curated by @zoedsy. Contact: zoedusy123@gmail.com.
Python
76.7%
JavaScript
23.3%
AI agents for scientific discovery: papers, tools, and an interactive bilingual atlas with detailed reading guides.
See the codeA curated list of papers, tools, and platforms on AI agents for scientific discovery (2023–2026) — spanning general science copilots, self-evolving agents and continual learning, benchmarks, physical sciences, life sciences, and social-science simulation.
Click any paper to understand what it does. Explore the collection on a timeline, then open a detailed reading guide with method steps, experimental results, original figures and tables, takeaways, authors, and institutions. Search by research question, author, or institution, and combine discipline and mechanism filters. No installation or sign-in needed.
推荐打开交互网页阅读: 在时间图谱中点击任意论文,查看具体方法、实验结果、原图表导读、主要结论及作者机构;支持中英切换、搜索和组合筛选。
Click the preview to explore the live atlas. 点击预览图,打开交互网页。
Quick links: Self-evolving agents & continual learning · Paper list · Reading and maintenance guide.
We're continually improving and expanding this collection. To add a paper, please see CONTRIBUTING.md or open an issue. For other inquiries: zoedusy123@gmail.com.
Type tags (blue):
Domain tags (green):
See CONTRIBUTING.md for tag definitions.
🌐 Cross-domain agentic systems, AI scientists, and research copilots.
[2026-07]
"Jacobian: Composable mathematics for agent-driven research experiments." code | project
[2026-06]
"Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy." Youran Sun et al. arXiv 2026. paper | code
[2026-06] "What's Missing in Autonomous Research? A Systematization of Systems, Benchmarks, and Verification." Xingyu Ren et al. Technical report 2026. paper
[2026-01] "Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts." Dhruv Trehan and Paras Chopra. arXiv 2026. paper
[2025-11]
"Kosmos: An AI Scientist for Autonomous Discovery." Ludovico Mitchener et al. (FutureHouse / Edison Scientific). arXiv 2025. paper | platform
[2025-10] "Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics." arXiv 2025. paper
[2025-08] "From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery." arXiv 2025. paper
[2025-04]
"The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search." Yutaro Yamada et al. arXiv 2025. paper | code
[2025-03] "AgentRxiv: Towards Collaborative Autonomous Research." Samuel Schmidgall and Michael Moor. arXiv 2025. paper | project
[2025-02] "Towards an AI co-scientist." Juraj Gottweis et al. (Google). arXiv 2025. paper | blog
[2025-01]
"Agent Laboratory: Using LLM Agents as Research Assistants." Samuel Schmidgall et al. EMNLP Findings 2025. paper | code
[2024-08] "MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents." Ruochen Li et al. arXiv 2024. paper | code
[2024-08]
"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery." Chris Lu et al. arXiv 2024. paper | code
[2024-06]
"AutoSurvey: Large Language Models Can Automatically Write Surveys." Yidong Wang et al. NeurIPS 2024. paper | code
[2023-12] "PaperQA: Retrieval-augmented generative agent for scientific research." Jakub Lála et al. arXiv 2023. paper
[2023-06] "Scientific discovery in the age of artificial intelligence." Hanchen Wang et al. Nature 2023. paper
🔄 Scientific agents that retain experience, acquire skills, adapt model parameters, or improve their own research machinery. Selected RSI (recursive self-improvement) foundations are included for their relevance to building and evaluating scientific agents.
Explore this topic in the interactive atlas → — compare papers on the timeline and open their detailed reading guides.
See the reading guide for mechanisms, scientific applications, evidence limits, and domain-specific works. Literature checked through 2026-09-12; entry dates refer to first publication, not the latest revision.
[2026-08]
"HypoForge: A Self-Improving Multi-Agent Framework for Automated Hypothesis Generation and Testing via Scientific Skill Learning." Ziqing Qian et al. arXiv 2026. paper
[2026-08] "Meta$^n$: Recursive Self-Improvement through Emergent Depth." Zae Myung Kim et al. arXiv 2026. paper | code
[2026-07] "SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition." Yuqi Tang et al. arXiv 2026. paper
[2026-06] "Evidence-Informed LLM Beliefs for Continual Scientific Discovery." Dhruv Agarwal et al. arXiv 2026. paper
[2026-06]
"MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery." Shangheng Du et al. arXiv 2026. paper | code
[2026-04] "EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale." Xinyu Zhu et al. arXiv 2026. paper | code
[2026-04]
"CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery." Ao Qu et al. COLM 2026. paper | code
[2026-03]
"Hyperagents." Jenny Zhang et al. arXiv 2026. paper | code
[2026-03]
"EvoScientist: Towards Multi-Agent Evolving AI Scientists for End-to-End Scientific Discovery." Yougang Lyu et al. arXiv 2026. paper | code
[2026-02]
"S1-NexusAgent: a Self-Evolving Agent Framework for Multidisciplinary Scientific Research." S1-NexusAgent Team. arXiv 2026. paper | code
[2026-01]
"Learning to Discover at Test Time." Mert Yuksekgonul et al. arXiv 2026. paper | code
[2025-05] "AlphaEvolve: A coding agent for scientific and algorithmic discovery." Alexander Novikov et al. arXiv 2025. paper | blog
[2025-05] "Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents." Jenny Zhang et al. arXiv 2025. paper | code
📊 Datasets, leaderboards, and evaluation frameworks.
[2026-08] "AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement." Yizhe Chi et al. arXiv 2026. paper
[2026-03] "ResearchClawBench" (code-only release). code | website
[2025-12] "Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows (SGI-Bench)." Wanghan Xu et al. (Shanghai AI Lab). arXiv 2025. paper | code | website
[2025-05] "MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research." Hui Chen et al. NeurIPS 2025 Datasets and Benchmarks Track. paper
[2025-05]
"AI-Researcher: Autonomous Scientific Innovation." HKUDS et al. arXiv 2025. paper
[2025-04] "PaperBench: Evaluating AI's Ability to Replicate AI Research." Giulio Starace et al. arXiv 2025. paper
[2024-10] "MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering." Jun Shern Chan et al. ICLR 2025. paper
[2024-10] "ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery." Ziru Chen et al. ICLR 2025. paper
⚛️ Physics · Chemistry · Earth Sciences · Astronomy · Materials.
[2026-08]
"AgentFEM: An AI-Native Open-Source Platform for Finite-Element Computing." Haoming Luo. Technical report 2026. paper | code | project
[2026-07]
"Harnessing agent memory to build lifelong AI partners for materials scientists." Siyu Liu et al. arXiv 2026. paper
[2026-06]
"Self-Evolving Scientific Agent Designs Physically Reasoned White-Box Fluid Control." Boai Sun et al. arXiv 2026. paper | code
[2026-05]
"GRAFT-ATHENA: Self-Improving Agentic Teams for Autonomous Discovery and Evolutionary Numerical Algorithms." Juan Diego Toscano, Zhaojie Chai, and George Em Karniadakis. arXiv 2026. paper
[2026-02]
"AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing." Jianda Du, Youran Sun, and Haizhao Yang. arXiv 2026. paper | code
[2026-02]
"Knowledge-driven autonomous materials research via collaborative multi-agent and robotic system (MARS)." Tongyu Shi et al. Matter 2026. paper
[2025-12]
"CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution." Xu Huang et al. arXiv 2025. paper
[2025-12]
"An Agentic Framework for Autonomous Materials Computation." arXiv 2025. paper
[2025-12]
"Hierarchical Multi-agent Large Language Model Reasoning for Autonomous Functional Materials Discovery." arXiv 2025. paper
[2025-08] "SciToolAgent: A knowledge-graph-driven scientific agent for multitool integration." Nature Computational Science 2025. paper
[2025-06]
"CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning." arXiv 2025. paper | code
[2025-04]
"MOFGen: System of Agentic AI for the Discovery of Metal-Organic Frameworks." Théo Jaffrelot Inizan et al. (UC Berkeley / Google DeepMind). arXiv 2025. paper
[2025-04]
"PriM: Principle-Inspired Material Discovery through Multi-Agent Collaboration." arXiv 2025. paper
[2024-12]
"SciAgents: Automating Scientific Discovery Through Bioinspired Multi-Agent Intelligent Graph Reasoning." Alireza Ghafarollahi and Markus J. Buehler. Advanced Materials 2025. paper | code
[2024-07]
"A Review of Large Language Models and Autonomous Agents in Chemistry." Mayk Caldas Ramos et al. arXiv 2024. paper
[2024-06]
"LLMatDesign: Autonomous Materials Discovery with Large Language Models." Shuyi Jia et al. arXiv 2024. paper
[2024-05]
"ChatMOF: An Artificial Intelligence System for Predicting and Generating Metal-Organic Frameworks Using Large Language Models." Yeonghun Kang and Jihan Kim. Nature Communications 2024. paper
[2023-12]
"Autonomous chemical research with large language models." Daniil A. Boiko et al. Nature 2023. paper
[2023-12]
"Augmenting large language models with chemistry tools (ChemCrow)." Andres M. Bran et al. Nature Machine Intelligence 2024. paper
🧬 Biology · Botany · Zoology · Microbiology · Neuroscience · Medicine.
[2026-09]
"ADMET-EvO: a self-evolving scientific agent for sustained research across heterogeneous tasks." Yiling Zhou et al. arXiv 2026. paper
[2026-04]
"An autonomous LLM-agent platform for computational binder design and conjugation-aware prioritization of antibody–drug conjugates." Ganggang Liu et al. bioRxiv 2026. paper | code
[2026-03] "Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents." Jacopo Teneggi et al. arXiv 2026. paper
[2026-03]
"Empowering AI data scientists using a multi-agent LLM framework with self-evolving capabilities for autonomous, tool-aware biomedical data analyses (BioMedAgent)." Dechao Bu et al. Nature Biomedical Engineering 2026. paper
[2026-02]
"A Multi-Agent Framework for Medical AI: Leveraging Fine-Tuned GPT, LLaMA, and DeepSeek R1 for Evidence-Based and Bias-Aware Clinical Query Processing." Naeimeh Nourmohammadi et al. arXiv 2026. paper
[2026-01]
"Agentic reinforcement learning empowers next-generation chemical language models for molecular design and synthesis." Hao Li et al. (Peking University). arXiv 2026. paper
[2026-01]
"Virtual lab of artificial intelligence agents accelerating nanobody design against SARS-CoV-2 variants." Hakjin Kim et al. International Journal of Biological Sciences 2026. paper
[2025-10]
"The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies." Kyle Swanson et al. Nature 2025. paper | code
[2025-07]
"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis." Haoyang Liu et al. arXiv 2025. paper
[2025-07]
"STELLA: Self-Evolving LLM Agent for Biomedical Research." Ruofan Jin et al. arXiv 2025. paper | code
[2025-05] "Robin: A multi-agent system for automating scientific discovery." Ali Essam Ghareeb et al. (FutureHouse). arXiv 2025. paper | blog
[2025-05] "Biomni: A General-Purpose Biomedical AI Agent." Kexin Huang et al. (Stanford). bioRxiv 2025. paper | platform
[2025-03]
"TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools." Shanghua Gao et al. (Harvard). arXiv 2025. paper | project | code
[2024-11]
"DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration." Sizhe Liu et al. arXiv 2024. paper
[2024-11] "TourSynbio-Agent: Validation of an LLM-based Multi-Agent Framework for Protein Engineering in Dry Lab and Wet Lab." Y. Shen et al. arXiv 2024. paper
[2024-10]
"An AI Agent for Fully Automated Multi-Omic Analyses." Juexiao Zhou et al. Advanced Science 2024. paper
[2024-10]
"BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments." Yusuf Roohani et al. arXiv 2024. paper
[2024-08]
"BioImage.IO Chatbot: a community-driven AI assistant for integrative computational bioimaging." Wanlu Lei et al. Nature Methods 2024. paper
[2024-08] "TourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineering." Y. Shen et al. arXiv 2024. paper
[2024-07]
"MMedAgent: Learning to Use Medical Tools with Multi-modal Agent." Binxu Li et al. arXiv 2024. paper
[2024-07]
"ClinicalAgent: Clinical Trial Multi-Agent System with Large Language Model-based Reasoning." Yue Ling et al. arXiv 2024. paper
[2024-07] "Empowering Biomedical Discovery with AI Agents." Shanghua Gao et al. arXiv 2024. paper
[2024-06]
"Omega — harnessing the power of large language models for bioimage analysis." Loïc A. Royer. Nature Methods 2024. paper
[2024-05]
"CellAgent: An LLM-driven Multi-Agent Framework for Automated Single-cell Data Analysis." Yihang Xiao et al. bioRxiv 2024. paper
[2024-05]
"BioInformatics Agent (BIA): Unleashing the Power of Large Language Models to Reshape Bioinformatics Workflow." Qi Xin et al. bioRxiv 2024. paper
[2024-05]
"Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents." Junkai Li et al. arXiv 2024. paper
[2024-04]
"CRISPR-GPT: An LLM Agent for Automated Design of Gene-Editing Experiments." Kaixuan Huang et al. arXiv 2024. paper
[2024-02] "ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning." Alireza Ghafarollahi and Markus J. Buehler. Digital Discovery 2024. paper
[2024-02]
"A multimodal generative AI copilot for human pathology." Ming Y. Lu et al. Nature 2024. paper
[2023-12]
"De novo drug design using reinforcement learning with multiple GPT agents." Xiuyuan Hu et al. NeurIPS 2023. paper
[2023-11]
"MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning." Xiangru Tang et al. arXiv 2023. paper
[2023-08]
"Zhongjing: Enhancing the Chinese Medical Capabilities of Large Language Model through Expert Feedback and Real-world Multi-turn Dialogue." S. Yang et al. arXiv 2023. paper
[2023-07]
"Epidemic modeling with generative agents." Ross Williams et al. arXiv 2023. paper
[2023-05]
"HuatuoGPT: Towards Taming Language Model to Be a Doctor." H. Zhang et al. arXiv 2023. paper
[2023-03] "Biological research and self-driving labs in deep space supported by artificial intelligence." Lauren M. Sanders et al. Nature Machine Intelligence 2023. paper
👥 Economics · sociology · political science · generative-agent simulation.
[2024-04] "ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models." Jinheon Baek et al. arXiv 2024. paper
[2023-11]
"ALYMPICS: Language Agents Meet Game Theory." Shaoguang Mao et al. arXiv 2023. paper
[2023-10]
"Lyfe Agents: Generative agents for low-cost real-time social interactions." Zhao Kaiya et al. arXiv 2023. paper
[2023-10]
"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents." Xuhui Zhou et al. arXiv 2023. paper
[2023-10]
"Large Language Model-Empowered Agents for Simulating Macroeconomic Activities." Nian Li et al. arXiv 2023. paper
[2023-10] "Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View." Jintian Zhang et al. arXiv 2023. paper
[2023-07]
"S³: Social-network Simulation System with Large Language Model-Empowered Agents." Chen Gao et al. arXiv 2023. paper
[2023-07] "The SocialAI school: Insights from developmental psychology towards artificial socio-cultural agents." Grgur Kovač et al. arXiv 2023. paper
[2023-07]
"Understanding the benefits and challenges of using large language model-based conversational agents for mental well-being support." Zilin Ma et al. arXiv 2023. paper
[2023-04]
"Generative agents: Interactive simulacra of human behavior." Joon Sung Park et al. arXiv 2023. paper
[2023-01] "Large language models as simulated economic agents: What can we learn from homo silicus?" John J. Horton. National Bureau of Economic Research 2023. paper
Contributions are very welcome! Please read CONTRIBUTING.md before opening a PR. For paper suggestions you can also open an issue using the Paper Submission template.
This list is released under CC0 1.0 Universal — to the extent possible under law, the maintainers have waived all copyright and related rights to this work. Underlying papers, code, and platforms remain under their respective licenses.
Curated by @zoedsy. Contact: zoedusy123@gmail.com.
Python
76.7%
JavaScript
23.3%