{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:51:47Z","timestamp":1792785107355,"version":"4.5.0"},"reference-count":189,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"National Natural Science Foundation of China","award":["22373085"],"award-info":[{"award-number":["22373085"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"National Key Research and Development Program of China","award":["2024YFA1306400"],"award-info":[{"award-number":["2024YFA1306400"]}]},{"name":"The Zhejiang Province Pioneer Plan","award":["2025C01189"],"award-info":[{"award-number":["2025C01189"]}]},{"name":"The Huadong Medicine Joint Fund of Zhejiang Provincial Natural Science Foundation of China","award":["LHDMZ25H300001"],"award-info":[{"award-number":["LHDMZ25H300001"]}],"id":[{"id":"https:\/\/ror.org\/04aqat463","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Drug Discov."],"DOI":"10.1038\/s44386-026-00075-0","type":"journal-article","created":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T13:02:45Z","timestamp":1791810165000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The rise of agentic AI in drug discovery from static tools to autonomous virtual scientists"],"prefix":"10.1038","volume":"3","author":[{"given":"Donghai","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meijing","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lexiao","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qun","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxia","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tingjun","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang-Yu","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,12]]},"reference":[{"key":"75_CR1","doi-asserted-by":"publisher","first-page":"788","DOI":"10.3390\/ph18060788","volume":"18","author":"V Malheiro","year":"2025","unstructured":"Malheiro, V., Santos, B., Figueiras, A. & Mascarenhas-Melo, F. The potential of artificial intelligence in pharmaceutical innovation: from drug discovery to clinical trials. Pharmaceuticals 18, 788 (2025).","journal-title":"Pharmaceuticals"},{"key":"75_CR2","doi-asserted-by":"publisher","first-page":"7035634","DOI":"10.1155\/2022\/7035634","volume":"2022","author":"X Liu","year":"2022","unstructured":"Liu, X., Yi, W., Xi, B. & Dai, Q. Identification of drug-disease associations using a random walk with restart method and supervised learning. Comput. Math. Methods Med. 2022, 7035634 (2022).","journal-title":"Comput. Math. Methods Med."},{"key":"75_CR3","doi-asserted-by":"publisher","first-page":"13347","DOI":"10.3390\/ijms232113347","volume":"23","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Qi, J. & Chen, X. Accurate prediction of epigenetic multi-targets with graph neural network-based feature extraction. Int. J. Mol. Sci. 23, 13347 (2022).","journal-title":"Int. J. Mol. Sci."},{"key":"75_CR4","doi-asserted-by":"publisher","first-page":"3049","DOI":"10.1016\/j.apsb.2022.02.002","volume":"12","author":"D Sun","year":"2022","unstructured":"Sun, D., Gao, W., Hu, H. & Zhou, S. Why 90% of clinical drug development fails and how to improve it? Acta Pharm. Sin. B. 12, 3049\u20133062 (2022).","journal-title":"Acta Pharm. Sin. B."},{"key":"75_CR5","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1038\/nrc2294","volume":"8","author":"R Clarke","year":"2008","unstructured":"Clarke, R. et al. The properties of high-dimensional data spaces: implications for exploring gene and protein expression data. Nat. Rev. Cancer 8, 37\u201349 (2008).","journal-title":"Nat. Rev. Cancer"},{"key":"75_CR6","doi-asserted-by":"publisher","first-page":"123888","DOI":"10.1016\/j.molliq.2023.123888","volume":"395","author":"I Salahshoori","year":"2024","unstructured":"Salahshoori, I. et al. Simulation-based approaches for drug delivery systems: navigating advancements, opportunities, and challenges. J. Mol. Liq. 395, 123888 (2024).","journal-title":"J. Mol. Liq."},{"key":"75_CR7","doi-asserted-by":"publisher","first-page":"46","DOI":"10.3390\/biotech12020046","volume":"12","author":"ACMAR Tassakka","year":"2023","unstructured":"Tassakka, A. C. M. A. R. et al. Docking studies and molecular dynamics simulations of potential inhibitors from the brown seaweed Sargassum polycystum (Phaeophyceae) against PLpro of SARS-CoV-2. BioTech 12, 46 (2023).","journal-title":"BioTech"},{"key":"75_CR8","doi-asserted-by":"publisher","first-page":"2208","DOI":"10.3390\/molecules23092208","volume":"23","author":"R Chen","year":"2018","unstructured":"Chen, R. et al. Machine learning for drug-target interaction prediction. Molecules 23, 2208 (2018).","journal-title":"Molecules"},{"key":"75_CR9","doi-asserted-by":"publisher","first-page":"2326","DOI":"10.1021\/acs.jpclett.5b00831","volume":"6","author":"K Hansen","year":"2015","unstructured":"Hansen, K. et al. Machine learning predictions of molecular properties: accurate many-body potentials and nonlocality in chemical space. J. Phys. Chem. Lett. 6, 2326\u20132331 (2015).","journal-title":"J. Phys. Chem. Lett."},{"key":"75_CR10","doi-asserted-by":"publisher","first-page":"113806","DOI":"10.1016\/j.addr.2021.05.016","volume":"175","author":"P Bannigan","year":"2021","unstructured":"Bannigan, P. et al. Machine learning directed drug formulation development. Adv. Drug Deliv. Rev. 175, 113806 (2021).","journal-title":"Adv. Drug Deliv. Rev."},{"key":"75_CR11","doi-asserted-by":"publisher","first-page":"4406","DOI":"10.1093\/bioinformatics\/btaa524","volume":"36","author":"L Chen","year":"2020","unstructured":"Chen, L. et al. TransformerCPI: improving compound\u2013protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments. Bioinformatics 36, 4406\u20134414 (2020).","journal-title":"Bioinformatics"},{"key":"75_CR12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-39856-w","volume":"14","author":"L Chen","year":"2023","unstructured":"Chen, L. et al. Sequence-based drug design as a concept in computational drug design. Nat. Commun. 14, 4217 (2023).","journal-title":"Nat. Commun."},{"key":"75_CR13","doi-asserted-by":"publisher","first-page":"6924","DOI":"10.1021\/acs.jmedchem.1c00421","volume":"64","author":"Z Wu","year":"2021","unstructured":"Wu, Z. et al. Mining toxicity information from large amounts of toxicity data. J. Med. Chem. 64, 6924\u20136936 (2021).","journal-title":"J. Med. Chem."},{"key":"75_CR14","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1186\/s13321-019-0397-9","volume":"11","author":"O Prykhodko","year":"2019","unstructured":"Prykhodko, O. et al. A de novo molecular generation method using latent vector based generative adversarial network. J. Cheminform. 11, 74 (2019).","journal-title":"J. Cheminform."},{"key":"75_CR15","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1038\/s42256-021-00403-1","volume":"3","author":"J Wang","year":"2021","unstructured":"Wang, J. et al. Multi-constraint molecular generation based on conditional transformer, knowledge distillation and reinforcement learning. Nat. Mach. Intell. 3, 914\u2013922 (2021).","journal-title":"Nat. Mach. Intell."},{"key":"75_CR16","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1038\/s41587-022-01618-2","volume":"41","author":"A Madani","year":"2023","unstructured":"Madani, A. et al. Large language models generate functional protein sequences across diverse families. Nat. Biotechnol. 41, 1099\u20131106 (2023).","journal-title":"Nat. Biotechnol."},{"key":"75_CR17","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.1038\/s41586-023-06415-8","volume":"620","author":"JL Watson","year":"2023","unstructured":"Watson, J. L. et al. De novo design of protein structure and function with rfdiffusion. Nature 620, 1089\u20131100 (2023).","journal-title":"Nature"},{"key":"75_CR18","doi-asserted-by":"publisher","unstructured":"Fehlis, Y. et al. Accelerating drug discovery through agentic AI: a multi-agent approach to laboratory automation in the DMTA cycle. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2507.09023 (2025).","DOI":"10.48550\/arXiv.2507.09023"},{"key":"75_CR19","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1007\/s10462-025-11422-4","volume":"59","author":"M Abou Ali","year":"2025","unstructured":"Abou Ali, M., Dornaika, F. & Charafeddine, J. Agentic AI: a comprehensive survey of architectures, applications, and future directions. Artif. Intell. Rev. 59, 11 (2025).","journal-title":"Artif. Intell. Rev."},{"key":"75_CR20","doi-asserted-by":"publisher","first-page":"6125","DOI":"10.1016\/j.cell.2024.09.022","volume":"187","author":"S Gao","year":"2024","unstructured":"Gao, S. et al. Empowering biomedical discovery with AI agents. Cell 187, 6125\u20136151 (2024).","journal-title":"Cell"},{"key":"75_CR21","doi-asserted-by":"publisher","first-page":"404","DOI":"10.3390\/fi17090404","volume":"17","author":"A Bandi","year":"2025","unstructured":"Bandi, A. et al. The rise of agentic AI: a review of definitions, frameworks, architectures, applications, evaluation metrics, and challenges. Future Internet 17, 404 (2025).","journal-title":"Future Internet"},{"key":"75_CR22","doi-asserted-by":"publisher","first-page":"104272","DOI":"10.1016\/j.drudis.2024.104272","volume":"30","author":"G Doron","year":"2025","unstructured":"Doron, G., Genway, S., Roberts, M. & Jasti, S. Generative AI: driving productivity and scientific breakthroughs in pharmaceutical r&d. Drug Discov. Today 30, 104272 (2025).","journal-title":"Drug Discov. Today"},{"key":"75_CR23","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1038\/s41586-023-06792-0","volume":"624","author":"DA Boiko","year":"2023","unstructured":"Boiko, D. A., MacKnight, R., Kline, B. & Gomes, G. Autonomous chemical research with large language models. Nature 624, 570\u2013578 (2023).","journal-title":"Nature"},{"key":"75_CR24","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1186\/s13321-025-00984-8","volume":"17","author":"S Ishida","year":"2025","unstructured":"Ishida, S., Sato, T., Honma, T. & Terayama, K. Large language models open new way of AI-assisted molecule design for chemists. J. Cheminform. 17, 36 (2025).","journal-title":"J. Cheminform."},{"key":"75_CR25","doi-asserted-by":"publisher","unstructured":"Zhang, Z. et al. OriGene: a self-evolving virtual disease biologist automating therapeutic target discovery. Preprint at https:\/\/doi.org\/10.1101\/2025.06.03.657658 (2025).","DOI":"10.1101\/2025.06.03.657658"},{"key":"75_CR26","doi-asserted-by":"publisher","first-page":"2055","DOI":"10.1021\/acs.jcim.5c02454","volume":"66","author":"J Ock","year":"2026","unstructured":"Ock, J. et al. Large language model agent for modular task execution in drug discovery. J. Chem. Inf. Model. 66, 2055\u20132068 (2026).","journal-title":"J. Chem. Inf. Model."},{"key":"75_CR27","doi-asserted-by":"publisher","unstructured":"Jin, R., Zhang, Z., Wang, M. & Cong, L. STELLA: self-evolving LLM agent for biomedical research. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2507.02004 (2025).","DOI":"10.48550\/arXiv.2507.02004"},{"key":"75_CR28","doi-asserted-by":"publisher","first-page":"101346","DOI":"10.1016\/j.patter.2025.101346","volume":"6","author":"Y Zheng","year":"2025","unstructured":"Zheng, Y. et al. Large language models for drug discovery and development. Patterns 6, 101346 (2025).","journal-title":"Patterns"},{"key":"75_CR29","doi-asserted-by":"publisher","first-page":"2514","DOI":"10.1039\/D4SC03921A","volume":"16","author":"MC Ramos","year":"2025","unstructured":"Ramos, M. C., Collison, C. J. & White, A. D. A review of large language models and autonomous agents in chemistry. Chem. Sci. 16, 2514\u20132572 (2025).","journal-title":"Chem. Sci."},{"key":"75_CR30","doi-asserted-by":"publisher","first-page":"bbag075","DOI":"10.1093\/bib\/bbag075","volume":"27","author":"C Qi","year":"2026","unstructured":"Qi, C. et al. Artificial intelligence agents for biological research: A survey. Brief. Bioinform. 27, bbag075 (2026).","journal-title":"Brief. Bioinform."},{"key":"75_CR31","doi-asserted-by":"crossref","unstructured":"Huynh, D. L. et al. AI agents in drug discovery: applications and case studies. Drug Discov. Today, 104650 (2026).","DOI":"10.1016\/j.drudis.2026.104650"},{"key":"75_CR32","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1145\/3715318","volume":"57","author":"Q Zhang","year":"2025","unstructured":"Zhang, Q. et al. Scientific large language models: a survey on biological & chemical domains. ACM Comput. Surv. 57, 161 (2025).","journal-title":"ACM Comput. Surv."},{"key":"75_CR33","doi-asserted-by":"publisher","unstructured":"Rong, D. et al. LiveProteinBench: a contamination-free benchmark for assessing models\u2019 specialized capabilities in protein science. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2512.22257 (2025).","DOI":"10.48550\/arXiv.2512.22257"},{"key":"75_CR34","doi-asserted-by":"publisher","unstructured":"Taylor, R. et al. Galactica: a large language model for science. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2211.09085 (2022).","DOI":"10.48550\/arXiv.2211.09085"},{"key":"75_CR35","doi-asserted-by":"publisher","unstructured":"Zhang, D. et al. ChemLLM: a chemical large language model. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2402.06852 (2024).","DOI":"10.48550\/arXiv.2402.06852"},{"key":"75_CR36","unstructured":"Xiao, Y., Sun, E., Jin, Y., Wang, Q. & Wang, W. ProteinGPT: multimodal LLM for protein property prediction and structure understanding. In ICLR 2025 Workshop on Machine Learning for Genomics Explorations (2025)."},{"key":"75_CR37","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1038\/s42256-025-01047-1","volume":"7","author":"BP de Almeida","year":"2025","unstructured":"de Almeida, B. P. et al. A multimodal conversational agent for DNA, RNA and protein tasks. Nat. Mach. Intell. 7, 928\u2013941 (2025).","journal-title":"Nat. Mach. Intell."},{"key":"75_CR38","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","volume":"379","author":"Z Lin","year":"2023","unstructured":"Lin, Z. et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 1123\u20131130 (2023).","journal-title":"Science"},{"key":"75_CR39","doi-asserted-by":"publisher","unstructured":"Bai, L. et al. Intern-S1: a scientific multimodal foundation model. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2508.15763 (2025).","DOI":"10.48550\/arXiv.2508.15763"},{"key":"75_CR40","doi-asserted-by":"publisher","unstructured":"Zou, Y. et al. Intern-S1-pro: scientific multimodal foundation model at trillion scale. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2603.25040 (2026).","DOI":"10.48550\/arXiv.2603.25040"},{"key":"75_CR41","doi-asserted-by":"publisher","unstructured":"Wei, J. et al. From AI for science to agentic science: a survey on autonomous scientific discovery. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2508.14111 (2025).","DOI":"10.48550\/arXiv.2508.14111"},{"key":"75_CR42","doi-asserted-by":"publisher","unstructured":"Huang, X. et al. Understanding the planning of LLM agents: a survey. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2402.02716 (2024).","DOI":"10.48550\/arXiv.2402.02716"},{"key":"75_CR43","doi-asserted-by":"publisher","first-page":"100213","DOI":"10.1016\/j.caeai.2024.100213","volume":"6","author":"G-G Lee","year":"2024","unstructured":"Lee, G.-G. et al. Applying large language models and chain-of-thought for automatic scoring. Comput. Educ. Artif. Intell. 6, 100213 (2024).","journal-title":"Comput. Educ. Artif. Intell."},{"key":"75_CR44","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-18622-6","volume":"15","author":"A Sinha","year":"2025","unstructured":"Sinha, A., Umakanthan, O. C. & Gajendran, S. DR-CoT: dynamic recursive chain of thought with meta reasoning for parameter efficient models. Sci. Rep. 15, 34773 (2025).","journal-title":"Sci. Rep."},{"key":"75_CR45","doi-asserted-by":"crossref","unstructured":"Yao, S. et al. Tree of thoughts: deliberate problem solving with large language models. In Thirty-seventh Conference on Neural Information Processing Systems (2023).","DOI":"10.52202\/075280-0517"},{"key":"75_CR46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCIAIG.2012.2186810","volume":"4","author":"CB Browne","year":"2012","unstructured":"Browne, C. B. et al. A survey of Monte Carlo tree search methods. IEEE Trans. Comput. Intell. AI Games 4, 1\u201343 (2012).","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"75_CR47","unstructured":"Yao, S. et al. ReAct: synergizing reasoning and acting in language models. In International Conference on Learning Representations (2023)."},{"key":"75_CR48","doi-asserted-by":"crossref","unstructured":"Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K. & Yao, S. Reflexion: language agents with verbal reinforcement learning. In Thirty-seventh Conference on Neural Information Processing Systems (2023).","DOI":"10.52202\/075280-0377"},{"key":"75_CR49","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/s41019-025-00296-9","volume":"10","author":"W Xu","year":"2025","unstructured":"Xu, W., Huang, C., Gao, S. & Shang, S. LLM-based agents for tool learning: A survey. Data Sci. Eng. 10, 533\u2013563 (2025).","journal-title":"Data Sci. Eng."},{"key":"75_CR50","doi-asserted-by":"publisher","unstructured":"Pan, Q. et al. Frogent: An end-to-end full-process drug design agent. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2508.10760 (2025).","DOI":"10.48550\/arXiv.2508.10760"},{"key":"75_CR51","doi-asserted-by":"publisher","unstructured":"Gao, S. et al. Democratizing AI scientists using tooluniverse. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2509.23426 (2025).","DOI":"10.48550\/arXiv.2509.23426"},{"key":"75_CR52","unstructured":"Wang, X. et al. Executable code actions elicit better LLM agents. In The Forty-first International Conference on Machine Learning (2024)."},{"key":"75_CR53","doi-asserted-by":"publisher","DOI":"10.1126\/science.adz4351","volume":"393","author":"K Huang","year":"2026","unstructured":"Huang, K. et al. Autonomous biomedical research with an artificial intelligence agent. Science 393, eadz4351 (2026).","journal-title":"Science"},{"key":"75_CR54","first-page":"19724","volume":"38","author":"W Zhong","year":"2024","unstructured":"Zhong, W. et al. MemoryBank: enhancing large language models with long-term memory. Proc. AAAI Conf. Artif. Intell. 38, 19724\u201319731 (2024).","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"75_CR55","doi-asserted-by":"publisher","first-page":"130193","DOI":"10.1016\/j.neucom.2025.130193","volume":"639","author":"Q Wang","year":"2025","unstructured":"Wang, Q. et al. Recursively summarizing enables long-term dialogue memory in large language models. Neurocomputing 639, 130193 (2025).","journal-title":"Neurocomputing"},{"key":"75_CR56","doi-asserted-by":"crossref","unstructured":"Sun, H., Zhang, Z. & Zeng, S. Preference-aware memory update for long-term LLM agents. In Findings of the Association for Computational Linguistics: ACL (2026).","DOI":"10.18653\/v1\/2026.findings-acl.38"},{"key":"75_CR57","doi-asserted-by":"publisher","first-page":"123855","DOI":"10.1109\/ACCESS.2025.3589241","volume":"13","author":"NA Akbar","year":"2025","unstructured":"Akbar, N. A., Dembani, R., Lenzitti, B. & Tegolo, D. RAG-driven memory architectures in conversational LLMs\u2014a literature review with insights into emerging agriculture data sharing. IEEE Access 13, 123855\u2013123880 (2025).","journal-title":"IEEE Access"},{"key":"75_CR58","doi-asserted-by":"publisher","unstructured":"\u00dcnl\u00fc, A., Rohr, P. & Celebi, A. An auditable agent platform for automated molecular optimisation. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2508.03444 (2025).","DOI":"10.48550\/arXiv.2508.03444"},{"key":"75_CR59","doi-asserted-by":"publisher","unstructured":"Tran, K.-T. et al. Multi-agent collaboration mechanisms: a survey of LLMs. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2501.06322 (2025).","DOI":"10.48550\/arXiv.2501.06322"},{"key":"75_CR60","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1002\/jrs.6808","volume":"56","author":"TT Khuat","year":"2025","unstructured":"Khuat, T. T., Bassett, R., Otte, E. & Gabrys, B. Uncertainty quantification using ensemble learning and Monte-Carlo sampling for performance prediction and monitoring in cell culture processes. J. Raman Spectrosc. 56, 623\u2013636 (2025).","journal-title":"J. Raman Spectrosc."},{"key":"75_CR61","doi-asserted-by":"publisher","unstructured":"Gao, B. et al. Pharmagents: Building a virtual pharma with large language model agents. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2503.22164 (2025).","DOI":"10.48550\/arXiv.2503.22164"},{"key":"75_CR62","doi-asserted-by":"publisher","first-page":"109396","DOI":"10.1016\/j.jmgm.2026.109396","volume":"146","author":"Q Yang","year":"2026","unstructured":"Yang, Q. et al. Drugagent: a multi-agent digital biosensor framework for interpretable virtual drug screening. J. Mol. Graph. Modell. 146, 109396 (2026).","journal-title":"J. Mol. Graph. Modell."},{"key":"75_CR63","doi-asserted-by":"publisher","first-page":"80950","DOI":"10.1109\/ACCESS.2024.3409051","volume":"12","author":"D Maldonado","year":"2024","unstructured":"Maldonado, D. et al. Multi-agent systems: a survey about its components, framework and workflow. IEEE Access 12, 80950\u201380975 (2024).","journal-title":"IEEE Access"},{"key":"75_CR64","doi-asserted-by":"publisher","first-page":"3897","DOI":"10.1007\/s10462-021-10097-x","volume":"55","author":"A Amirkhani","year":"2022","unstructured":"Amirkhani, A. & Barshooi, A. H. Consensus in multi-agent systems: a review. Artif. Intell. Rev. 55, 3897\u20133935 (2022).","journal-title":"Artif. Intell. Rev."},{"key":"75_CR65","doi-asserted-by":"crossref","unstructured":"Tang, X. et al. MedAgents: large language models as collaborators for zero-shot medical reasoning. In ICLR 2024 Workshop on Large Language Model (LLM) Agents (2024).","DOI":"10.18653\/v1\/2024.findings-acl.33"},{"key":"75_CR66","doi-asserted-by":"publisher","unstructured":"Yang, Z. et al. Drugmcts: a drug repurposing framework combining multi-agent, RAG and Monte Carlo tree search. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2507.07426 (2025).","DOI":"10.48550\/arXiv.2507.07426"},{"key":"75_CR67","doi-asserted-by":"crossref","unstructured":"Yang, Y. et al. AgentNet: decentralized evolutionary coordination for LLM-based multi-agent systems. In Thirty-eighth Conference on Neural Information Processing Systems (2025).","DOI":"10.32388\/WS0VIM"},{"key":"75_CR68","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1038\/s41586-026-10652-y","volume":"655","author":"AE Ghareeb","year":"2026","unstructured":"Ghareeb, A. E. et al. A multi-agent system for automating scientific discovery. Nature 655, 497\u2013505 (2026).","journal-title":"Nature"},{"key":"75_CR69","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1007\/s10462-021-09996-w","volume":"55","author":"S Gronauer","year":"2022","unstructured":"Gronauer, S. & Diepold, K. Multi-agent deep reinforcement learning: a survey. Artif. Intell. Rev. 55, 895\u2013943 (2022).","journal-title":"Artif. Intell. Rev."},{"key":"75_CR70","doi-asserted-by":"crossref","unstructured":"Liang, Y., Wu, H., Wang, H. & Cai, H. Asynchronous credit assignment for multi-agent reinforcement learning. In The Thirty-fourth International Joint Conference on Artificial Intelligence (2025).","DOI":"10.24963\/ijcai.2025\/20"},{"key":"75_CR71","doi-asserted-by":"publisher","unstructured":"Ehtesham, A., Singh, A., Gupta, G. K. & Kumar, S. A survey of agent interoperability protocols: model context protocol (MCP), agent communication protocol (ACP), agent-to-agent protocol (A2A), and agent network protocol (ANP). Preprint at https:\/\/doi.org\/10.48550\/arXiv.2505.02279 (2025).","DOI":"10.48550\/arXiv.2505.02279"},{"key":"75_CR72","doi-asserted-by":"publisher","unstructured":"Lu, Y., Hu, Y., Zhao, X. & Cao, J. DyTopo: dynamic topology routing for multi-agent reasoning via semantic matching. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2602.06039 (2026).","DOI":"10.48550\/arXiv.2602.06039"},{"key":"75_CR73","doi-asserted-by":"publisher","unstructured":"Yu, Z. et al. Multi-agent memory from a computer architecture perspective: visions and challenges ahead. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2603.10062 (2026).","DOI":"10.48550\/arXiv.2603.10062"},{"key":"75_CR74","doi-asserted-by":"publisher","first-page":"1793","DOI":"10.1021\/acs.jmedchem.4c02543","volume":"68","author":"X Shen","year":"2025","unstructured":"Shen, X. et al. TarIKGC: a target identification tool using semantics-enhanced Knowledge Graph completion with application to CDK2 inhibitor discovery. J. Med. Chem. 68, 1793\u20131809 (2025).","journal-title":"J. Med. Chem."},{"key":"75_CR75","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1038\/s41586-026-10644-y","volume":"655","author":"J Gottweis","year":"2026","unstructured":"Gottweis, J. et al. Accelerating scientific discovery with co-scientist. Nature 655, 487\u2013496 (2026).","journal-title":"Nature"},{"key":"75_CR76","unstructured":"Rein, D. et al. GPQA: a graduate-level Google-proof Q&A benchmark. In The First Conference on Language Modeling (2024)."},{"key":"75_CR77","doi-asserted-by":"publisher","first-page":"e08751","DOI":"10.1002\/advs.202508751","volume":"12","author":"Y Guan","year":"2025","unstructured":"Guan, Y. et al. AI-assisted drug re-purposing for human liver fibrosis. Adv. Sci. 12, e08751 (2025).","journal-title":"Adv. Sci."},{"key":"75_CR78","doi-asserted-by":"publisher","first-page":"6654","DOI":"10.1016\/j.cell.2025.08.018","volume":"188","author":"JR Penad\u00e9s","year":"2025","unstructured":"Penad\u00e9s, J. R. et al. AI mirrors experimental science to uncover a mechanism of gene transfer crucial to bacterial evolution. Cell 188, 6654\u20136665.e6652 (2025).","journal-title":"Cell"},{"key":"75_CR79","doi-asserted-by":"publisher","first-page":"6636","DOI":"10.1016\/j.cell.2025.08.019","volume":"188","author":"L He","year":"2025","unstructured":"He, L. et al. Chimeric infective particles expand species boundaries in phage-inducible chromosomal island mobilization. Cell 188, 6636\u20136653.e6617 (2025).","journal-title":"Cell"},{"key":"75_CR80","doi-asserted-by":"publisher","first-page":"2407094","DOI":"10.1002\/advs.202407094","volume":"11","author":"J Zhou","year":"2024","unstructured":"Zhou, J. et al. An AI agent for fully automated multi-omic analyses. Adv. Sci. 11, 2407094 (2024).","journal-title":"Adv. Sci."},{"key":"75_CR81","doi-asserted-by":"publisher","unstructured":"Xin, Q. et al. Bioinformatics agent (bia): unleashing the power of large language models to reshape bioinformatics workflow. Preprint at https:\/\/doi.org\/10.1101\/2024.05.22.595240 (2024).","DOI":"10.1101\/2024.05.22.595240"},{"key":"75_CR82","unstructured":"Xiao, Y. et al. CellAgent: LLM-driven multi-agent framework for natural language-based single-cell analysis. In The Fourteenth International Conference on Learning Representations (2026)."},{"key":"75_CR83","doi-asserted-by":"publisher","first-page":"101611","DOI":"10.1016\/j.patter.2026.101611","volume":"7","author":"H Su","year":"2026","unstructured":"Su, H. et al. Biomaster: Multi-agent system for automated bioinformatics analysis workflow. Patterns 7, 101611 (2026).","journal-title":"Patterns"},{"key":"75_CR84","doi-asserted-by":"publisher","unstructured":"Niyakan, S. & Qian, X. Phenograph: a multi-agent framework for phenotype-driven discovery in spatial transcriptomics data augmented with knowledge graphs. Preprint at https:\/\/doi.org\/10.1101\/2025.06.06.658341 (2025).","DOI":"10.1101\/2025.06.06.658341"},{"key":"75_CR85","doi-asserted-by":"publisher","unstructured":"Zhang, F., Zhao, Y., Zhang, W. & Lai, L. Bioscientist agent: designing LLM-biomedical agents with KG-augmented RL reasoning modules for drug repurposing and mechanistic of action elucidation. Preprint at https:\/\/doi.org\/10.1101\/2025.08.08.669291 (2025).","DOI":"10.1101\/2025.08.08.669291"},{"key":"75_CR86","doi-asserted-by":"publisher","first-page":"102537","DOI":"10.1016\/j.sbi.2023.102537","volume":"79","author":"S Luukkonen","year":"2023","unstructured":"Luukkonen, S., van den Maagdenberg, H. W., Emmerich, M. T. M. & van Westen, G. J. P. Artificial intelligence in multi-objective drug design. Curr. Opin. Struct. Biol. 79, 102537 (2023).","journal-title":"Curr. Opin. Struct. Biol."},{"key":"75_CR87","doi-asserted-by":"publisher","first-page":"e1680","DOI":"10.1002\/wcms.1680","volume":"13","author":"S Ishida","year":"2023","unstructured":"Ishida, S. et al. ChemTSv2: functional molecular design using de novo molecule generator. WIREs Comput. Mol. Sci. 13, e1680 (2023).","journal-title":"WIREs Comput. Mol. Sci."},{"key":"75_CR88","doi-asserted-by":"publisher","unstructured":"Yu, J. et al. Collaborative expert LLMs guided multi-objective molecular optimization. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2503.03503 (2025).","DOI":"10.48550\/arXiv.2503.03503"},{"key":"75_CR89","doi-asserted-by":"publisher","first-page":"1447","DOI":"10.1038\/s42256-023-00759-6","volume":"5","author":"S Liu","year":"2023","unstructured":"Liu, S. et al. Multi-modal molecule structure\u2013text model for text-based retrieval and editing. Nat. Mach. Intell. 5, 1447\u20131457 (2023).","journal-title":"Nat. Mach. Intell."},{"key":"75_CR90","doi-asserted-by":"publisher","unstructured":"Wei, Z. et al. Fleming: an AI agent for antibiotic discovery in mycobacterium tuberculosis. Preprint at https:\/\/doi.org\/10.1101\/2025.04.01.646719 (2025).","DOI":"10.1101\/2025.04.01.646719"},{"key":"75_CR91","doi-asserted-by":"publisher","first-page":"103224","DOI":"10.1016\/j.sbi.2026.103224","volume":"97","author":"JJ Chubb","year":"2026","unstructured":"Chubb, J. J., Boyle, A. L. & Albanese, K. I. Rational protein design. Curr. Opin. Struct. Biol. 97, 103224 (2026).","journal-title":"Curr. Opin. Struct. Biol."},{"key":"75_CR92","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-026-06878-0","volume":"13","author":"Y Wu","year":"2026","unstructured":"Wu, Y. et al. A unified dataset for antibody and nanobody design including sequence, structure, and binding affinity data. Sci. Data 13, 295 (2026).","journal-title":"Sci. Data"},{"key":"75_CR93","doi-asserted-by":"publisher","first-page":"100366","DOI":"10.1016\/j.medntd.2025.100366","volume":"26","author":"J Yao","year":"2025","unstructured":"Yao, J. & Wang, X. Artificial intelligence in de novo protein design. Med. Nov. Technol. Devices 26, 100366 (2025).","journal-title":"Med. Nov. Technol. Devices"},{"key":"75_CR94","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.1039\/D4DD00013G","volume":"3","author":"A Ghafarollahi","year":"2024","unstructured":"Ghafarollahi, A. & Buehler, M. J. Protagents: protein discovery via large language model multi-agent collaborations combining physics and machine learning. Digital Discovery 3, 1389\u20131409 (2024).","journal-title":"Digital Discovery"},{"key":"75_CR95","doi-asserted-by":"publisher","first-page":"1070","DOI":"10.1038\/s41586-023-06728-8","volume":"623","author":"JB Ingraham","year":"2023","unstructured":"Ingraham, J. B. et al. Illuminating protein space with a programmable generative model. Nature 623, 1070\u20131078 (2023).","journal-title":"Nature"},{"key":"75_CR96","doi-asserted-by":"publisher","unstructured":"Wu, R. et al. High-resolution de novo structure prediction from primary sequence. Preprint at https:\/\/doi.org\/10.1101\/2022.07.21.500999 (2022).","DOI":"10.1101\/2022.07.21.500999"},{"key":"75_CR97","doi-asserted-by":"publisher","first-page":"2619","DOI":"10.1093\/bioinformatics\/btl448","volume":"22","author":"E Eyal","year":"2006","unstructured":"Eyal, E., Yang, L.-W. & Bahar, I. Anisotropic network model: systematic evaluation and a new web interface. Bioinformatics 22, 2619\u20132627 (2006).","journal-title":"Bioinformatics"},{"key":"75_CR98","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1038\/s41586-025-09442-9","volume":"646","author":"K Swanson","year":"2025","unstructured":"Swanson, K. et al. The virtual lab of AI agents designs new SARS-CoV-2 nanobodies. Nature 646, 716\u2013723 (2025).","journal-title":"Nature"},{"key":"75_CR99","doi-asserted-by":"publisher","unstructured":"Evans, R. et al. Protein complex prediction with AlphaFold-multimer. Preprint at https:\/\/doi.org\/10.1101\/2021.10.04.463034 (2021).","DOI":"10.1101\/2021.10.04.463034"},{"key":"75_CR100","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1002\/prot.26422","volume":"91","author":"VS Boorla","year":"2023","unstructured":"Boorla, V. S. et al. De novo design and rosetta-based assessment of high-affinity antibody variable regions (Fv) against the SARS-CoV-2 spike receptor binding domain (RBD). Proteins 91, 196\u2013208 (2023).","journal-title":"Proteins"},{"key":"75_CR101","doi-asserted-by":"publisher","unstructured":"Jin, R. et al. BioLab: end-to-end autonomous life sciences research with multi-agents system integrating biological foundation models. Preprint at https:\/\/doi.org\/10.1101\/2025.09.03.674085 (2025).","DOI":"10.1101\/2025.09.03.674085"},{"key":"75_CR102","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1208\/s12248-021-00593-x","volume":"23","author":"N Terranova","year":"2021","unstructured":"Terranova, N., Venkatakrishnan, K. & Benincosa, L. J. Application of machine learning in translational medicine: current status and future opportunities. AAPS J. 23, 74 (2021).","journal-title":"AAPS J."},{"key":"75_CR103","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf601","volume":"26","author":"T Yang","year":"2025","unstructured":"Yang, T. et al. The rise and potential opportunities of large language model agents in bioinformatics and biomedicine. Brief. Bioinform. 26, bbaf601 (2025).","journal-title":"Brief. Bioinform."},{"key":"75_CR104","doi-asserted-by":"publisher","first-page":"10808","DOI":"10.1021\/acs.jcim.5c01938","volume":"65","author":"JC G\u00f3mez-Tamayo","year":"2025","unstructured":"G\u00f3mez-Tamayo, J. C. et al. MolAgent: biomolecular property estimation in the agentic era. J. Chem. Inf. Model. 65, 10808\u201310818 (2025).","journal-title":"J. Chem. Inf. Model."},{"key":"75_CR105","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1021\/acs.jcim.4c01345","volume":"65","author":"H Huang","year":"2025","unstructured":"Huang, H. et al. ProtChat: an AI multi-agent for automated protein analysis leveraging GPT-4 and protein language model. J. Chem. Inf. Model. 65, 62\u201370 (2025).","journal-title":"J. Chem. Inf. Model."},{"key":"75_CR106","doi-asserted-by":"publisher","unstructured":"Lee, N. et al. RAG-enhanced collaborative LLM agents for drug discovery. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2502.17506 (2025).","DOI":"10.48550\/arXiv.2502.17506"},{"key":"75_CR107","doi-asserted-by":"crossref","unstructured":"Yue, L., Xing, S., Chen, J. & Fu, T. ClinicalAgent: clinical trial multi-agent system with large language model-based reasoning. In The Fifteenth ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (2024).","DOI":"10.1145\/3698587.3701359"},{"key":"75_CR108","doi-asserted-by":"publisher","unstructured":"Wang, E. et al. TxGemma: efficient and agentic LLMs for therapeutics. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2504.06196 (2025).","DOI":"10.48550\/arXiv.2504.06196"},{"key":"75_CR109","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1186\/s13321-020-00472-1","volume":"12","author":"S Genheden","year":"2020","unstructured":"Genheden, S. et al. AiZynthFinder: a fast, robust and flexible open-source software for retrosynthetic planning. J. Cheminform. 12, 70 (2020).","journal-title":"J. Cheminform."},{"key":"75_CR110","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1038\/s42004-023-00911-8","volume":"6","author":"S Hong","year":"2023","unstructured":"Hong, S. et al. Retrosynthetic planning with experience-guided Monte Carlo tree search. Commun. Chem. 6, 120 (2023).","journal-title":"Commun. Chem."},{"key":"75_CR111","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1186\/s13321-024-00860-x","volume":"16","author":"L Saigiridharan","year":"2024","unstructured":"Saigiridharan, L. et al. AiZynthFinder 4.0: developments based on learnings from 3 years of industrial application. J. Cheminform. 16, 57 (2024).","journal-title":"J. Cheminform."},{"key":"75_CR112","doi-asserted-by":"publisher","unstructured":"Baker, F. N. et al. Larc: Towards human-level constrained retrosynthesis planning through an agentic framework. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2508.11860 (2025).","DOI":"10.48550\/arXiv.2508.11860"},{"key":"75_CR113","doi-asserted-by":"publisher","first-page":"102812","DOI":"10.1016\/j.matt.2026.102812","volume":"9","author":"AM Bran","year":"2026","unstructured":"Bran, A. M. et al. Chemical reasoning in LLMs unlocks strategy-aware synthesis planning and reaction mechanism elucidation. Matter 9, 102812 (2026).","journal-title":"Matter"},{"key":"75_CR114","doi-asserted-by":"crossref","unstructured":"Liu, W. et al. Retro-r1: LLM-based agentic retrosynthesis. In The Thirty-ninth Annual Conference on Neural Information Processing Systems (2025).","DOI":"10.52202\/085713-2378"},{"key":"75_CR115","doi-asserted-by":"publisher","first-page":"2285","DOI":"10.1039\/D5DD00151J","volume":"4","author":"K Ochiai","year":"2025","unstructured":"Ochiai, K. et al. Automating care by self-maintainability for full laboratory automation. Digit. Discov. 4, 2285\u20132297 (2025).","journal-title":"Digit. Discov."},{"key":"75_CR116","doi-asserted-by":"publisher","first-page":"12534","DOI":"10.1021\/jacs.4c17738","volume":"147","author":"T Song","year":"2025","unstructured":"Song, T. et al. A multiagent-driven robotic AI chemist enabling autonomous chemical research on demand. J. Am. Chem. Soc. 147, 12534\u201312545 (2025).","journal-title":"J. Am. Chem. Soc."},{"key":"75_CR117","first-page":"207","volume":"3","author":"AJ Oyejide","year":"2025","unstructured":"Oyejide, A. J., Adekunle, Y. A., Abodunrin, O. D. & Atoyebi, E. O. Artificial intelligence, computational tools and robotics for drug discovery, development, and delivery. Intell. Pharm. 3, 207\u2013224 (2025).","journal-title":"Intell. Pharm."},{"key":"75_CR118","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1007\/s11030-021-10266-8","volume":"25","author":"V Gallego","year":"2021","unstructured":"Gallego, V. et al. AI in drug development: a multidisciplinary perspective. Mol. Diversity 25, 1461\u20131479 (2021).","journal-title":"Mol. Diversity"},{"key":"75_CR119","doi-asserted-by":"publisher","first-page":"23889","DOI":"10.1021\/acsomega.5c00549","volume":"10","author":"FJN Ferreira","year":"2025","unstructured":"Ferreira, F. J. N. & Carneiro, A. S. AI-driven drug discovery: a comprehensive review. ACS Omega 10, 23889\u201323903 (2025).","journal-title":"ACS Omega"},{"key":"75_CR120","doi-asserted-by":"publisher","first-page":"186345","DOI":"10.1007\/s11704-024-40231-1","volume":"18","author":"L Wang","year":"2024","unstructured":"Wang, L. et al. A survey on large language model based autonomous agents. Front. Comput. Sci. 18, 186345 (2024).","journal-title":"Front. Comput. Sci."},{"key":"75_CR121","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s10462-025-11471-9","volume":"59","author":"SS Chowa","year":"2026","unstructured":"Chowa, S. S. et al. From language to action: a review of large language models as autonomous agents and tool users. Artif. Intell. Rev. 59, 71 (2026).","journal-title":"Artif. Intell. Rev."},{"key":"75_CR122","doi-asserted-by":"publisher","first-page":"962","DOI":"10.1038\/s43588-025-00849-y","volume":"5","author":"K Ding","year":"2025","unstructured":"Ding, K. et al. Scitoolagent: a knowledge-graph-driven scientific agent for multitool integration. Nat. Comput. Sci. 5, 962\u2013972 (2025).","journal-title":"Nat. Comput. Sci."},{"key":"75_CR123","doi-asserted-by":"crossref","unstructured":"Jin, Q., Dhingra, B., Liu, Z., Cohen, W. & Lu, X. PubMedQA: a dataset for biomedical research question answering. In The 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (2019).","DOI":"10.18653\/v1\/D19-1259"},{"key":"75_CR124","doi-asserted-by":"crossref","unstructured":"Wang, Y. et al. MMLU-Pro: a more robust and challenging multi-task language understanding benchmark. In Thirty-eighth Conference on Neural Information Processing Systems (2024).","DOI":"10.52202\/079017-3018"},{"key":"75_CR125","doi-asserted-by":"publisher","first-page":"1139","DOI":"10.1038\/s41586-025-09962-4","volume":"649","author":"L Phan","year":"2026","unstructured":"Phan, L. et al. A benchmark of expert-level academic questions to assess AI capabilities. Nature 649, 1139\u20131146 (2026).","journal-title":"Nature"},{"key":"75_CR126","doi-asserted-by":"publisher","first-page":"9023","DOI":"10.1039\/D2SC02763A","volume":"13","author":"Z Zhong","year":"2022","unstructured":"Zhong, Z. et al. Root-aligned SMILES: a tight representation for chemical reaction prediction. Chem. Sci. 13, 9023\u20139034 (2022).","journal-title":"Chem. Sci."},{"key":"75_CR127","unstructured":"Huang, K. et al. Therapeutics Data Commons: machine learning datasets and tasks for drug discovery and development. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2021)."},{"key":"75_CR128","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1038\/nbt.1990","volume":"29","author":"MI Davis","year":"2011","unstructured":"Davis, M. I. et al. Comprehensive analysis of kinase inhibitor selectivity. Nat. Biotechnol. 29, 1046\u20131051 (2011).","journal-title":"Nat. Biotechnol."},{"key":"75_CR129","doi-asserted-by":"publisher","first-page":"4200","DOI":"10.1021\/acs.jcim.0c00411","volume":"60","author":"PG Francoeur","year":"2020","unstructured":"Francoeur, P. G. et al. Three-dimensional convolutional neural networks and a cross-docked data set for structure-based drug design. J. Chem. Inf. Model. 60, 4200\u20134215 (2020).","journal-title":"J. Chem. Inf. Model."},{"key":"75_CR130","doi-asserted-by":"publisher","unstructured":"Laurent, J. M. et al. Lab-bench: measuring capabilities of language models for biology research. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2407.10362 (2024).","DOI":"10.48550\/arXiv.2407.10362"},{"key":"75_CR131","unstructured":"Chen, Z. et al. ScienceAgentBench: toward rigorous assessment of language agents for data-driven scientific discovery. In International Conference on Learning Representations (2025)."},{"key":"75_CR132","doi-asserted-by":"publisher","unstructured":"Mitchener, L. et al. BixBench: a comprehensive benchmark for LLM-based agents in computational biology. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2503.00096 (2025).","DOI":"10.48550\/arXiv.2503.00096"},{"key":"75_CR133","doi-asserted-by":"crossref","unstructured":"Edwards, N. et al. RExBench: can coding agents autonomously implement AI research extensions? In The Sixty-fourth Annual Meeting of the Association for Computational Linguistics (2026).","DOI":"10.18653\/v1\/2026.acl-long.745"},{"key":"75_CR134","doi-asserted-by":"publisher","unstructured":"Smbatyan, K. et al. Can AI agents design and implement drug discovery pipelines? Preprint at https:\/\/doi.org\/10.48550\/arXiv.2504.19912 (2025).","DOI":"10.48550\/arXiv.2504.19912"},{"key":"75_CR135","unstructured":"Sun, Q. et al. ScienceBoard: evaluating multimodal autonomous agents in realistic scientific workflows. In The Fourteenth International Conference on Learning Representations (2026)."},{"key":"75_CR136","doi-asserted-by":"crossref","unstructured":"Li, R. et al. LabUtopia: high-fidelity simulation and hierarchical benchmark for scientific embodied agents. In Thirty-eighth Conference on Neural Information Processing Systems (2025).","DOI":"10.52202\/085713-1158"},{"key":"75_CR137","doi-asserted-by":"publisher","unstructured":"Ye, B. et al. Claw-Eval: toward trustworthy evaluation of autonomous agents. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2604.06132 (2026).","DOI":"10.48550\/arXiv.2604.06132"},{"key":"75_CR138","doi-asserted-by":"publisher","unstructured":"Liu, Y. et al. Trajad: trajectory anomaly detection for trustworthy LLM agents. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2602.06443 (2026).","DOI":"10.48550\/arXiv.2602.06443"},{"key":"75_CR139","unstructured":"AlSayyad, A., Huang, K. Y. & Pal, R. AgentTrace: a structured logging framework for agent system observability. In AAAI Workshop on Trust and Control in Agentic AI (2026)."},{"key":"75_CR140","doi-asserted-by":"publisher","first-page":"108522","DOI":"10.1016\/j.biotechadv.2025.108522","volume":"79","author":"K Jeung","year":"2025","unstructured":"Jeung, K. et al. Cell-free systems: a synthetic biology tool for rapid prototyping in metabolic engineering. Biotechnol. Adv. 79, 108522 (2025).","journal-title":"Biotechnol. Adv."},{"key":"75_CR141","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1038\/s41578-023-00588-4","volume":"8","author":"Z Ren","year":"2023","unstructured":"Ren, Z. et al. Autonomous experiments using active learning and AI. Nat. Rev. Mater. 8, 563\u2013564 (2023).","journal-title":"Nat. Rev. Mater."},{"key":"75_CR142","unstructured":"Zheng, T. et al. NewtonBench: benchmarking generalizable scientific law discovery in LLM agents. In The Fourteenth International Conference on Learning Representations (2026)."},{"key":"75_CR143","doi-asserted-by":"publisher","first-page":"100804","DOI":"10.1016\/j.patter.2023.100804","volume":"4","author":"S Kapoor","year":"2023","unstructured":"Kapoor, S. & Narayanan, A. Leakage and the reproducibility crisis in machine-learning-based science. Patterns 4, 100804 (2023).","journal-title":"Patterns"},{"key":"75_CR144","unstructured":"Carlini, N. et al. Quantifying memorization across neural language models. In The Eleventh International Conference on Learning Representations (2023)."},{"key":"75_CR145","doi-asserted-by":"publisher","unstructured":"Yan, J. et al. Biominer: a multi-modal system for automated mining of protein-ligand bioactivity data from literature. Preprint at https:\/\/doi.org\/10.1101\/2025.04.22.648951 (2025).","DOI":"10.1101\/2025.04.22.648951"},{"key":"75_CR146","doi-asserted-by":"publisher","first-page":"100844","DOI":"10.1016\/j.websem.2024.100844","volume":"85","author":"E Lavrinovics","year":"2025","unstructured":"Lavrinovics, E., Biswas, R., Bjerva, J. & Hose, K. Knowledge graphs, large language models, and hallucinations: an NLP perspective. J. Web Semant. 85, 100844 (2025).","journal-title":"J. Web Semant."},{"key":"75_CR147","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-80571-3","volume":"14","author":"Y Cong","year":"2024","unstructured":"Cong, Y. Manner implicatures in large language models. Sci. Rep. 14, 29113 (2024).","journal-title":"Sci. Rep."},{"key":"75_CR148","unstructured":"Liu, Z. et al. KAN: Kolmogorov\u2013Arnold networks. In The Thirteenth International Conference on Learning Representations (2025)."},{"key":"75_CR149","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1126\/science.add2187","volume":"378","author":"J Dauparas","year":"2022","unstructured":"Dauparas, J. et al. Robust deep learning\u2013based protein sequence design using ProteinMPNN. Science 378, 49\u201356 (2022).","journal-title":"Science"},{"key":"75_CR150","doi-asserted-by":"publisher","unstructured":"Liu, J., Zhao, X., Shang, X. & Shen, Z. Dive into Claude code: the design space of today\u2019s and future AI agent systems. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2604.14228 (2026).","DOI":"10.48550\/arXiv.2604.14228"},{"key":"75_CR151","doi-asserted-by":"publisher","unstructured":"Wang, Y. et al. OpenClaw-RL: train any agent simply by talking. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2603.10165 (2026).","DOI":"10.48550\/arXiv.2603.10165"},{"key":"75_CR152","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-27222-7","volume":"12","author":"J Koehler Leman","year":"2021","unstructured":"Koehler Leman, J. et al. Ensuring scientific reproducibility in bio-macromolecular modeling via extensive, automated benchmarks. Nat. Commun. 12, 6947 (2021).","journal-title":"Nat. Commun."},{"key":"75_CR153","doi-asserted-by":"crossref","unstructured":"Zhu, C. et al. FS-Researcher: test-time scaling for long-horizon research tasks with file-system-based agents. In The Sixty-fourth Annual Meeting of the Association for Computational Linguistics (2026).","DOI":"10.18653\/v1\/2026.acl-long.288"},{"key":"75_CR154","doi-asserted-by":"publisher","unstructured":"Wu, Z. & Gartner, G. Context cartography: toward structured governance of contextual space in large language model systems. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2603.20578 (2026).","DOI":"10.48550\/arXiv.2603.20578"},{"key":"75_CR155","doi-asserted-by":"publisher","first-page":"1649155","DOI":"10.3389\/frai.2025.1649155","volume":"8","author":"T Hartung","year":"2025","unstructured":"Hartung, T. AI, agentic models and lab automation for scientific discovery - the beginning of scaince. Front Artif. Intell. 8, 1649155 (2025).","journal-title":"Front Artif. Intell."},{"key":"75_CR156","doi-asserted-by":"publisher","first-page":"101370","DOI":"10.1016\/j.patter.2025.101370","volume":"6","author":"F Xu","year":"2025","unstructured":"Xu, F. et al. Toward large reasoning models: a survey of reinforced reasoning with large language models. Patterns 6, 101370 (2025).","journal-title":"Patterns"},{"key":"75_CR157","unstructured":"Wang, G. et al. Voyager: an open-ended embodied agent with large language models. Trans. Mach. Learn. Res. (2024)."},{"key":"75_CR158","doi-asserted-by":"publisher","unstructured":"Schulman, J. et al. Proximal policy optimization algorithms. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1707.06347 (2017).","DOI":"10.48550\/arXiv.1707.06347"},{"key":"75_CR159","doi-asserted-by":"publisher","unstructured":"Wu, X. Sailing by the stars: a survey on reward models and learning strategies for learning from rewards. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2505.02686 (2025).","DOI":"10.48550\/arXiv.2505.02686"},{"key":"75_CR160","doi-asserted-by":"crossref","unstructured":"Xi, Z. et al. AgentPRM: process reward models for LLM agents via step-wise promise and progress. In Proc. ACM Web Conference (2026).","DOI":"10.1145\/3774904.3792551"},{"key":"75_CR161","doi-asserted-by":"publisher","unstructured":"Wang, Z. et al. Rro: LLM agent optimization through rising reward trajectories. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2505.20737 (2025).","DOI":"10.48550\/arXiv.2505.20737"},{"key":"75_CR162","unstructured":"Liu, X. et al. Agentic reinforcement learning with implicit step rewards. In The Fourteenth International Conference on Learning Representations (2026)."},{"key":"75_CR163","doi-asserted-by":"publisher","unstructured":"Choudhury, S. Process reward models for LLM agents: practical framework and directions. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2502.10325 (2025).","DOI":"10.48550\/arXiv.2502.10325"},{"key":"75_CR164","doi-asserted-by":"crossref","unstructured":"Liu, S., Liang, Z., Lyu, X. & Amato, C. LLM collaboration with multi-agent reinforcement learning. In The Fortieth AAAI Conference on Artificial Intelligence (2026).","DOI":"10.1609\/aaai.v40i38.40487"},{"key":"75_CR165","unstructured":"Dong, G. et al. Agentic reinforced policy optimization. In The Fourteenth International Conference on Learning Representations (2026)."},{"key":"75_CR166","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-59231-1","volume":"16","author":"RB Canty","year":"2025","unstructured":"Canty, R. B. et al. Science acceleration and accessibility with self-driving labs. Nat. Commun. 16, 3856 (2025).","journal-title":"Nat. Commun."},{"key":"75_CR167","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adv7932","volume":"10","author":"AI Cooper","year":"2025","unstructured":"Cooper, A. I. et al. Accelerating discovery in natural science laboratories with AI and robotics: perspectives and challenges. Sci. Robot. 10, eadv7932 (2025).","journal-title":"Sci. Robot."},{"key":"75_CR168","doi-asserted-by":"publisher","first-page":"100111","DOI":"10.1016\/j.device.2023.100111","volume":"1","author":"RP Wierenga","year":"2023","unstructured":"Wierenga, R. P. et al. PyLabRobot: an open-source, hardware-agnostic interface for liquid-handling robots and accessories. Device 1, 100111 (2023).","journal-title":"Device"},{"key":"75_CR169","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1002\/elsc.202000053","volume":"21","author":"M Porr","year":"2021","unstructured":"Porr, M. et al. Implementing a digital infrastructure for the lab using a central laboratory server and the SiLA2 communication standard. Eng. Life Sci. 21, 208\u2013219 (2021).","journal-title":"Eng. Life Sci."},{"key":"75_CR170","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1038\/s41570-025-00747-x","volume":"9","author":"SX Leong","year":"2025","unstructured":"Leong, S. X. et al. Steering towards safe self-driving laboratories. Nat. Rev. Chem. 9, 707\u2013722 (2025).","journal-title":"Nat. Rev. Chem."},{"key":"75_CR171","doi-asserted-by":"crossref","unstructured":"Moshkovich, D. & Zeltyn, S. Taming uncertainty via automation: observing, analyzing, and optimizing agentic AI systems. In The Fortieth IEEE\/ACM International Conference on Automated Software Engineering (2025).","DOI":"10.1109\/ASE63991.2025.00327"},{"key":"75_CR172","doi-asserted-by":"publisher","first-page":"2104","DOI":"10.1039\/D5DD00018A","volume":"4","author":"RJ Hickman","year":"2025","unstructured":"Hickman, R. J. et al. Anubis: Bayesian optimization with unknown feasibility constraints for scientific experimentation. Digit. Discov. 4, 2104\u20132122 (2025).","journal-title":"Digit. Discov."},{"key":"75_CR173","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1038\/s41587-025-02650-8","volume":"43","author":"M Wang","year":"2025","unstructured":"Wang, M. et al. A call for built-in biosecurity safeguards for generative AI tools. Nat. Biotechnol. 43, 845\u2013847 (2025).","journal-title":"Nat. Biotechnol."},{"key":"75_CR174","doi-asserted-by":"publisher","first-page":"618","DOI":"10.1038\/s41591-024-03445-1","volume":"31","author":"DA Alber","year":"2025","unstructured":"Alber, D. A. et al. Medical large language models are vulnerable to data-poisoning attacks. Nat. Med. 31, 618\u2013626 (2025).","journal-title":"Nat. Med."},{"key":"75_CR175","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-63913-1","volume":"16","author":"X Tang","year":"2025","unstructured":"Tang, X. et al. Risks of AI scientists: prioritizing safeguarding over autonomy. Nat. Commun. 16, 8317 (2025).","journal-title":"Nat. Commun."},{"key":"75_CR176","doi-asserted-by":"publisher","unstructured":"Xu, Z., Jain, S. & Kankanhalli, M. Hallucination is inevitable: an innate limitation of large language models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2401.11817 (2024).","DOI":"10.48550\/arXiv.2401.11817"},{"key":"75_CR177","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1038\/s42256-022-00465-9","volume":"4","author":"F Urbina","year":"2022","unstructured":"Urbina, F., Lentzos, F., Invernizzi, C. & Ekins, S. Dual use of artificial-intelligence-powered drug discovery. Nat. Mach. Intell. 4, 189\u2013191 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"75_CR178","doi-asserted-by":"publisher","first-page":"1900","DOI":"10.3390\/molecules28041900","volume":"28","author":"B Tan","year":"2023","unstructured":"Tan, B. et al. Progress of artificial intelligence in drug synthesis and prospect of its application in nitrification of energetic materials. Molecules 28, 1900 (2023).","journal-title":"Molecules"},{"key":"75_CR179","doi-asserted-by":"publisher","first-page":"100076","DOI":"10.1016\/j.aichem.2024.100076","volume":"2","author":"S Yu","year":"2024","unstructured":"Yu, S., Ran, N. & Liu, J. Large-language models: the game-changers for materials science research. Artif. Intell. Chem. 2, 100076 (2024).","journal-title":"Artif. Intell. Chem."},{"key":"75_CR180","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1038\/s42256-024-00832-8","volume":"6","author":"AM Bran","year":"2024","unstructured":"Bran, A. M. et al. Augmenting large language models with chemistry tools. Nat. Mach. Intell. 6, 525\u2013535 (2024).","journal-title":"Nat. Mach. Intell."},{"key":"75_CR181","doi-asserted-by":"publisher","first-page":"D1388","DOI":"10.1093\/nar\/gkaa971","volume":"49","author":"S Kim","year":"2020","unstructured":"Kim, S. et al. PubChem in 2021: new data content and improved web interfaces. Nucleic Acids Res. 49, D1388\u2013D1395 (2020).","journal-title":"Nucleic Acids Res."},{"key":"75_CR182","doi-asserted-by":"publisher","first-page":"D523","DOI":"10.1093\/nar\/gkac1052","volume":"51","author":"Consortium, T. U.","year":"2022","unstructured":"Consortium, T. U. UniProt: the universal protein knowledgebase in 2023. Nucleic Acids Res. 51, D523\u2013D531 (2022).","journal-title":"Nucleic Acids Res."},{"key":"75_CR183","doi-asserted-by":"publisher","first-page":"18385","DOI":"10.1021\/acsomega.4c00262","volume":"9","author":"C Zhang","year":"2024","unstructured":"Zhang, C., Arun, A. & Lapkin, A. A. Completing and balancing database excerpted chemical reactions with a hybrid mechanistic-machine learning approach. ACS Omega 9, 18385\u201318399 (2024).","journal-title":"ACS Omega"},{"key":"75_CR184","volume":"2","author":"D Mandl Kenneth","year":"2025","unstructured":"Mandl Kenneth, D. Unseen commercial forces could undermine artificial intelligence decision support. NEJM AI 2, AIp2400922 (2025).","journal-title":"NEJM AI"},{"key":"75_CR185","doi-asserted-by":"publisher","first-page":"100181","DOI":"10.1016\/j.fhj.2024.100181","volume":"11","author":"K Fotheringham","year":"2024","unstructured":"Fotheringham, K. & Smith, H. Accidental injustice: healthcare AI legal responsibility must be prospectively planned prior to its adoption. Future Health J. 11, 100181 (2024).","journal-title":"Future Health J."},{"key":"75_CR186","doi-asserted-by":"publisher","first-page":"e42936","DOI":"10.2196\/42936","volume":"2","author":"CT Berdahl","year":"2023","unstructured":"Berdahl, C. T. et al. Strategies to improve the impact of artificial intelligence on health equity: scoping review. JMIR AI 2, e42936 (2023).","journal-title":"JMIR AI"},{"key":"75_CR187","doi-asserted-by":"publisher","DOI":"10.1186\/s12910-025-01198-1","volume":"26","author":"E Ratti","year":"2025","unstructured":"Ratti, E., Morrison, M. & Jakab, I. Ethical and social considerations of applying artificial intelligence in healthcare\u2014a two-pronged scoping review. BMC Med. Ethics 26, 68 (2025).","journal-title":"BMC Med. Ethics"},{"key":"75_CR188","doi-asserted-by":"publisher","unstructured":"Zhang, Z. et al. Agent-SafetyBench: Evaluating the safety of LLM agents. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2412.14470 (2024).","DOI":"10.48550\/arXiv.2412.14470"},{"key":"75_CR189","unstructured":"Zhang, H. et al. Agent security bench (ASB): formalizing and benchmarking attacks and defenses in LLM-based agents. In The Thirteenth International Conference on Learning Representations (2025)."}],"container-title":["npj Drug Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s44386-026-00075-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44386-026-00075-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s44386-026-00075-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:27:14Z","timestamp":1791826034000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s44386-026-00075-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,12]]},"references-count":189,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["75"],"URL":"https:\/\/doi.org\/10.1038\/s44386-026-00075-0","relation":{},"ISSN":["3005-1452"],"issn-type":[{"value":"3005-1452","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,12]]},"assertion":[{"value":"27 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 October 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing financial or non-financial interests. C.Y.H. and T.H. are Editorial Board Members of npj Drug Discovery. C.Y.H. and T.H. were not involved in the journal\u2019s review of, or decisions related to, this manuscript.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"43"}}