{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T00:04:54Z","timestamp":1793923494743,"version":"4.8.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"8125","license":[{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nature"],"published-print":{"date-parts":[[2026,7,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Large language models (LLMs) show great potential for clinical decision-making, yet most applications remain narrow, task-specific chat tools rather than systems integrated into clinical workflows\n                    <jats:sup>1,2<\/jats:sup>\n                    . However, building physician copilots will require models that operate within the electronic health record (EHR), with governed access to patient data and the ability to initiate permitted EHR actions within defined safety constraints. Yet it remains unproven whether such a system can manage patient cases with physician-level performance. Here we show that MIRA (Medical Intelligence for Reasoning and Action), an autonomous artificial intelligence agent operating in a sandboxed EHR environment, can navigate a large clinical action space to obtain patient histories; order and interpret laboratory, imaging and microbiology tests; generate differential diagnoses; and formulate treatment plans such as prescribing medications, scheduling surgical procedures and planning admissions. In simulations on real patient cases spanning multiple diagnoses, MIRA outperformed physicians in diagnostic accuracy and made guideline-concordant, medication-safe and appropriate admission decisions. Compared with previous LLM applications that addressed isolated subtasks or provided free-text advice, these results suggest that an EHR-integrated artificial intelligence agent can turn clinical intent into structured, actionable EHR operations, possibly making it a more effective decision-support partner for physicians. Further work is needed to establish generalization, safety and governance through prospective, real-world studies.\n                  <\/jats:p>","DOI":"10.1038\/s41586-026-10675-5","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T15:02:41Z","timestamp":1781708561000},"page":"1282-1291","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":42,"title":["Towards autonomous medical artificial intelligence agents"],"prefix":"10.1038","volume":"655","author":[{"given":"Dyke","family":"Ferber","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lars","family":"Hilgers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christiane","family":"H\u00f6per","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benedict","family":"Kinny-K\u00f6ster","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan-Niklas","family":"Eckardt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katharina","family":"Egger-Heidrich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1175-2406","authenticated-orcid":false,"given":"Marius","family":"Bill","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5501-4050","authenticated-orcid":false,"given":"Martin M. K.","family":"Schneider","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2925-8438","authenticated-orcid":false,"given":"Jan","family":"Clusmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lejla","family":"Kadric","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcel","family":"Oehme","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2184-8337","authenticated-orcid":false,"given":"Maximilian","family":"Mayrhofer-Schmid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Oeser","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0407-7617","authenticated-orcid":false,"given":"Georg","family":"W\u00f6lflein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isabella C.","family":"Wiest","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan Moritz","family":"Middeke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A. John","family":"Iafrate","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9605-0728","authenticated-orcid":false,"given":"Daniel","family":"Truhn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1276-7802","authenticated-orcid":false,"given":"Dirk","family":"J\u00e4ger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3730-5348","authenticated-orcid":false,"given":"Jakob Nikolas","family":"Kather","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"10675_CR1","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1038\/s41586-025-08866-7","volume":"642","author":"T Tu","year":"2025","unstructured":"Tu, T. et al. Towards conversational diagnostic artificial intelligence. Nature 642, 442\u2013450 (2025).","journal-title":"Nature"},{"key":"10675_CR2","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1038\/s43856-023-00370-1","volume":"3","author":"J Clusmann","year":"2023","unstructured":"Clusmann, J. et al. The future landscape of large language models in medicine. Commun. Med. 3, 141 (2023).","journal-title":"Commun. Med."},{"key":"10675_CR3","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172\u2013180 (2023).","journal-title":"Nature"},{"key":"10675_CR4","unstructured":"Nori, H. et al. Can generalist foundation models outcompete special-purpose tuning? Case study in medicine. Preprint at https:\/\/arxiv.org\/abs\/2311.16452 (2023)."},{"key":"10675_CR5","doi-asserted-by":"crossref","unstructured":"Brodeur, P. G. et al. Performance of a large language model on the reasoning tasks of a physician. Science 392, 524\u2013527 (2026).","DOI":"10.1126\/science.adz4433"},{"key":"10675_CR6","unstructured":"Nori, H. et al. From Medprompt to o1: exploration of run-time strategies for medical challenge problems and beyond. Preprint at https:\/\/arxiv.org\/abs\/2411.03590 (2024)."},{"key":"10675_CR7","unstructured":"Yang, L. et al. Advancing multimodal medical capabilities of Gemini. Preprint at https:\/\/arxiv.org\/abs\/2405.03162 (2024)."},{"key":"10675_CR8","doi-asserted-by":"publisher","DOI":"10.1056\/AIcs2300235","volume":"1","author":"D Ferber","year":"2024","unstructured":"Ferber, D. et al. GPT-4 for information retrieval and comparison of medical oncology guidelines. NEJM AI 1, AIcs2300235 (2024).","journal-title":"NEJM AI"},{"key":"10675_CR9","doi-asserted-by":"publisher","unstructured":"Wiest, I. C. et al. LLM-AIx: an open source pipeline for information extraction from unstructured medical text based on privacy preserving large language models. Preprint at medRxiv https:\/\/doi.org\/10.1101\/2024.09.02.24312917 (2024).","DOI":"10.1101\/2024.09.02.24312917"},{"key":"10675_CR10","unstructured":"Kwan, K. Large language models are good medical coders, if provided with tools. Preprint at https:\/\/arxiv.org\/abs\/2407.12849 (2024)."},{"key":"10675_CR11","unstructured":"Introducing computer use, a new Claude 3.5 Sonnet, and Claude 3.5 Haiku. Anthropic https:\/\/www.anthropic.com\/news\/3-5-models-and-computer-use (2024)."},{"key":"10675_CR12","doi-asserted-by":"crossref","unstructured":"Zakka, C. et al. Almanac Copilot: towards autonomous electronic health record navigation. Preprint at https:\/\/arxiv.org\/abs\/2405.07896 (2024).","DOI":"10.21203\/rs.3.rs-6102516\/v1"},{"key":"10675_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, Y. et al. MedAgentBench: a realistic virtual EHR environment to benchmark medical LLM agents. Preprint at https:\/\/arxiv.org\/abs\/2501.14654 (2025).","DOI":"10.32388\/VN3YH7"},{"key":"10675_CR14","doi-asserted-by":"publisher","unstructured":"Schmidgall, S. et al. AgentClinic: a multimodal benchmark for tool-using clinical AI agents. NPJ Digit. Med. https:\/\/doi.org\/10.1038\/s41746-026-02674-7 (2026).","DOI":"10.1038\/s41746-026-02674-7"},{"key":"10675_CR15","unstructured":"Nori, H. et al. Sequential diagnosis with language models. Preprint at https:\/\/arxiv.org\/abs\/2506.22405 (2025)."},{"key":"10675_CR16","unstructured":"Korom, R. et al. AI-based clinical decision support for primary care: a real-world study. OpenAI https:\/\/cdn.openai.com\/pdf\/a794887b-5a77-4207-bb62-e52c900463f1\/penda_paper.pdf (2025)."},{"key":"10675_CR17","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x","volume":"10","author":"AEW Johnson","year":"2023","unstructured":"Johnson, A. E. W. et al. MIMIC-IV, a freely accessible electronic health record dataset. Sci. Data 10, 1 (2023).","journal-title":"Sci. Data"},{"key":"10675_CR18","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","volume":"30","author":"P Hager","year":"2024","unstructured":"Hager, P. et al. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nat. Med. 30, 2613\u20132622 (2024).","journal-title":"Nat. Med."},{"key":"10675_CR19","unstructured":"Palepu, A. et al. Towards conversational AI for disease management. Preprint at https:\/\/arxiv.org\/abs\/2503.06074 (2025)."},{"key":"10675_CR20","doi-asserted-by":"publisher","first-page":"3166","DOI":"10.1007\/s11606-020-06087-4","volume":"35","author":"F Toscano","year":"2020","unstructured":"Toscano, F. et al. How physicians spend their work time: an ecological momentary assessment. J. Gen. Intern. Med. 35, 3166\u20133172 (2020).","journal-title":"J. Gen. Intern. Med."},{"key":"10675_CR21","doi-asserted-by":"publisher","first-page":"2293","DOI":"10.1038\/s41562-024-02024-1","volume":"8","author":"M Vaccaro","year":"2024","unstructured":"Vaccaro, M., Almaatouq, A. & Malone, T. When combinations of humans and AI are useful: a systematic review and meta-analysis. Nat. Hum. Behav. 8, 2293\u20132303 (2024).","journal-title":"Nat. Hum. Behav."},{"key":"10675_CR22","doi-asserted-by":"crossref","unstructured":"Cairns, C. & Kang, K. National Hospital Ambulatory Medical Care Survey: 2022 Emergency Department Summary Tables (National Center for Health Statistics, 2022).","DOI":"10.15620\/cdc:121911"},{"key":"10675_CR23","unstructured":"Johnson, A. MIMIC lab items ID to LOINC mapping. GitHub https:\/\/github.com\/MIT-LCP\/mimic-code\/blob\/e39825259beaa9d6bc9b99160049a5d251852aae\/mimic-iv\/mapping\/d_labitems_to_loinc.csv (2023)."},{"key":"10675_CR24","unstructured":"Sturua, S. et al. jina-embeddings-v3: multilingual embeddings with task LoRA. Preprint at https:\/\/arxiv.org\/abs\/2409.10173 (2024)."},{"key":"10675_CR25","unstructured":"High-performance vector search at scale. Qdrant https:\/\/qdrant.tech\/ (2024)."},{"key":"10675_CR26","doi-asserted-by":"publisher","first-page":"1400","DOI":"10.1038\/ajg.2013.218","volume":"108","author":"S Tenner","year":"2013","unstructured":"Tenner, S., Baillie, J., DeWitt, J. & Vege, S. S. American College of Gastroenterology Guideline: management of acute pancreatitis. Am. J. Gastroenterol. 108, 1400\u20131415 (2013).","journal-title":"Am. J. Gastroenterol."},{"key":"10675_CR27","doi-asserted-by":"publisher","DOI":"10.1186\/s13017-020-00306-3","volume":"15","author":"S Di Saverio","year":"2020","unstructured":"Di Saverio, S. et al. Diagnosis and treatment of acute appendicitis: 2020 update of the WSES Jerusalem guidelines. World J. Emerg. Surg. 15, 27 (2020).","journal-title":"World J. Emerg. Surg."},{"key":"10675_CR28","doi-asserted-by":"publisher","DOI":"10.1038\/s41572-020-0162-4","volume":"6","author":"A Tursi","year":"2020","unstructured":"Tursi, A. et al. Colonic diverticular disease. Nat. Rev. Dis. Primers 6, 21 (2020).","journal-title":"Nat. Rev. Dis. Primers"},{"key":"10675_CR29","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1016\/j.annonc.2023.08.009","volume":"34","author":"T Conroy","year":"2023","unstructured":"Conroy, T. et al. Pancreatic cancer: ESMO Clinical Practice Guideline for diagnosis, treatment and follow-up. Ann. Oncol. 34, 987\u20131002 (2023).","journal-title":"Ann. Oncol."},{"key":"10675_CR30","doi-asserted-by":"publisher","first-page":"e45","DOI":"10.1164\/rccm.201908-1581ST","volume":"200","author":"JP Metlay","year":"2019","unstructured":"Metlay, J. P. et al. Diagnosis and treatment of adults with community-acquired pneumonia. An official clinical practice guideline of the American Thoracic Society and Infectious Diseases Society of America. Am. J. Respir. Crit. Care Med. 200, e45\u2013e67 (2019).","journal-title":"Am. J. Respir. Crit. Care Med."},{"key":"10675_CR31","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1093\/eurheartj\/ehz405","volume":"41","author":"SV Konstantinides","year":"2020","unstructured":"Konstantinides, S. V. et al. 2019 ESC Guidelines for the diagnosis and management of acute pulmonary embolism developed in collaboration with the European Respiratory Society (ERS). Eur. Heart J. 41, 543\u2013603 (2020).","journal-title":"Eur. Heart J."},{"key":"10675_CR32","unstructured":"Bonkat, G. et al. EAU Guidelines on Urological Infections (European Association of Urology, 2024)."},{"key":"10675_CR33","unstructured":"A free and open source global good: powering interoperability around the world for 23 years. HAPI FHIR https:\/\/hapifhir.io\/ (2024)."},{"key":"10675_CR34","unstructured":"Islam, M. N. FHIR resources. https:\/\/pypi.org\/project\/fhir.resources\/ (2024)."},{"key":"10675_CR35","unstructured":"OpenAI et al. OpenAI o1 system card. Preprint at https:\/\/arxiv.org\/abs\/2412.16720 (2024)."},{"key":"10675_CR36","unstructured":"Building effective agents. Anthropic https:\/\/www.anthropic.com\/research\/building-effective-agents (2024)."},{"key":"10675_CR37","doi-asserted-by":"crossref","unstructured":"Zeng, Y. et al. How Johnny can persuade LLMs to jailbreak them: rethinking persuasion to challenge AI safety by humanizing LLMs. Preprint at https:\/\/arxiv.org\/abs\/2401.06373 (2024).","DOI":"10.18653\/v1\/2024.acl-long.773"},{"key":"10675_CR38","doi-asserted-by":"publisher","unstructured":"Meincke, L. et al. Call me a jerk: persuading AI to comply with objectionable requests. Wharton School Research Paper https:\/\/doi.org\/10.2139\/ssrn.5357179 (2025).","DOI":"10.2139\/ssrn.5357179"},{"key":"10675_CR39","unstructured":"Wataoka, K., Takahashi, T. & Ri, R. Self-preference bias in LLM-as-a-judge. Preprint at https:\/\/arxiv.org\/abs\/2410.21819 (2025)."},{"key":"10675_CR40","doi-asserted-by":"publisher","DOI":"10.1186\/s13017-020-00336-x","volume":"15","author":"M Pisano","year":"2020","unstructured":"Pisano, M. et al. 2020 World Society of Emergency Surgery updated guidelines for the diagnosis and treatment of acute calculus cholecystitis. World J. Emerg. Surg. 15, 61 (2020).","journal-title":"World J. Emerg. Surg."},{"key":"10675_CR41","doi-asserted-by":"publisher","DOI":"10.1186\/s13017-019-0247-0","volume":"14","author":"A Lepp\u00e4niemi","year":"2019","unstructured":"Lepp\u00e4niemi, A. et al. 2019 WSES guidelines for the management of severe acute pancreatitis. World J. Emerg. Surg. 14, 27 (2019).","journal-title":"World J. Emerg. Surg."},{"key":"10675_CR42","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1097\/DCR.0000000000001679","volume":"63","author":"J Hall","year":"2020","unstructured":"Hall, J. et al. The American Society of Colon and Rectal Surgeons clinical practice guidelines for the treatment of left-sided colonic diverticulitis. Dis. Colon Rectum 63, 728\u2013747 (2020).","journal-title":"Dis. Colon Rectum"},{"key":"10675_CR43","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1053\/j.ajkd.2023.08.009","volume":"83","author":"H Al Lawati","year":"2024","unstructured":"Al Lawati, H., Blair, B. M. & Larnard, J. Urinary tract infections: core curriculum 2024. Am. J. Kidney Dis. 83, 90\u2013100 (2024).","journal-title":"Am. J. Kidney Dis."},{"key":"10675_CR44","doi-asserted-by":"publisher","first-page":"4693","DOI":"10.1182\/bloodadvances.2020001830","volume":"4","author":"TL Ortel","year":"2020","unstructured":"Ortel, T. L. et al. American Society of Hematology 2020 guidelines for management of venous thromboembolism: treatment of deep vein thrombosis and pulmonary embolism. Blood Adv. 4, 4693\u20134738 (2020).","journal-title":"Blood Adv"}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41586-026-10675-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-026-10675-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-026-10675-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T18:10:24Z","timestamp":1785521424000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41586-026-10675-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":44,"journal-issue":{"issue":"8125","published-print":{"date-parts":[[2026,7,30]]}},"alternative-id":["10675"],"URL":"https:\/\/doi.org\/10.1038\/s41586-026-10675-5","relation":{},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,17]]},"assertion":[{"value":"29 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"J.N.K. declares consulting services for Bioptimus, France; Panakeia, UK; AstraZeneca, UK; and MultiplexDx, Slovakia. Furthermore, he holds shares in StratifAI, Germany, Synagen, Germany, Ignition Lab, Germany; has received an institutional research grant by GSK; and has received honoraria by AstraZeneca, Bayer, Daiichi Sankyo, Eisai, Janssen, Merck, MSD, BMS, Roche, Pfizer and Fresenius. J.-N.E. declares consulting services for AstraZeneca, Novartis, Janssen. Furthermore, he holds shares in Cancilico, has received an institutional research grant from Novartis and has received honoraria from Amgen, AstraZeneca, Janssen, Novartis and Pfizer. D.T. received honoraria for lectures by Bayer and holds shares in StratifAI GmbH, Germany. A.J.I. declares royalties from ArcherDx\/IDT, consulting for AstraZeneca, Paige.AI, Intellia, Repare Therapeutics and SequreDx. D.F. holds shares in and is employed at Synagen AI GmbH. G.W. declares consulting services for Synagen AI GmbH. C.H. is employed at Synagen AI GmbH and received honoraria from AstraZeneca. I.C.W. received honoraria from AstraZeneca. J.C. has received honoraria from Johnson & Johnson. The other authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}]}}