{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,8]],"date-time":"2026-11-08T11:25:28Z","timestamp":1794137128232,"version":"4.8.0"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"8139","license":[{"start":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T00:00:00Z","timestamp":1792540800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T00:00:00Z","timestamp":1792540800000},"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":[[2026,11,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Large language models are enabling a new generation of health agents, yet their ability to address the diverse needs of individuals in everyday health settings remains underexplored\n                    <jats:sup>1,2<\/jats:sup>\n                    . Here we developed a comprehensive personal health agent that reasons over multimodal data from consumer wellness devices and medical records to provide personalized health support. Through analysis of web search and health forum queries, together with user-centred research involving end users and health experts, we identified four key user journeys: general health knowledge, personal data interpretation, wellness advice, and symptom assessment. These journeys informed three specialist sub-agents: (1) a data science agent that analyses longitudinal wearable and medical data, incorporating population-level statistics to contextualize numerical insights; (2) a health domain expert agent that integrates personal and contextual data with health knowledge to generate personalized insights; and (3) a health coach agent that synthesizes insights, supports multi-turn interaction and goal setting, applies specified psychological strategies and tracks progress. We integrated these capabilities in the personal health agent, an open-source multi-agent framework for dynamic, personalized health interactions. We evaluated the sub-agents and full system across 11 benchmark tasks using automated and human evaluation, with more than 7,000 annotations and 1,350\u2009h of effort from health experts and end users. This represents the most comprehensive evaluation of a personal health agent thus far and provides a concrete foundation for improving access to high-quality personalized health support more broadly.\n                  <\/jats:p>","DOI":"10.1038\/s41586-026-11161-8","type":"journal-article","created":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T15:02:14Z","timestamp":1792594934000},"page":"197-207","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["The anatomy of a personal health agent"],"prefix":"10.1038","volume":"659","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9141-3809","authenticated-orcid":false,"given":"A. Ali","family":"Heydari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ken","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vidya","family":"Srinivas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4664-3186","authenticated-orcid":false,"given":"Akshay","family":"Paruchuri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7394-5409","authenticated-orcid":false,"given":"Zhihan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid","family":"Palangi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nova","family":"Hammerquist","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0155-7412","authenticated-orcid":false,"given":"Ahmed A.","family":"Metwally","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7098-6336","authenticated-orcid":false,"given":"Brent","family":"Winslow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kumar","family":"Ayush","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7634-8295","authenticated-orcid":false,"given":"Yuzhe","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5647-3577","authenticated-orcid":false,"given":"Girish","family":"Narayanswamy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maxwell A.","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jake","family":"Garrison","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuel","family":"Schmidgall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amy","family":"Armento Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jenny","family":"Vafeiadou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ben","family":"Graef","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isaac R.","family":"Galatzer-Levy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik","family":"Schenck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Barakat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Javier","family":"Perez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1410-9432","authenticated-orcid":false,"given":"Jacqueline","family":"Shreibati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3313-430X","authenticated-orcid":false,"given":"John","family":"Hernandez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony Z.","family":"Faranesh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naghmeh","family":"Rezaei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3665-8114","authenticated-orcid":false,"given":"Javier L.","family":"Prieto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Conor","family":"Heneghan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiening","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Malhotra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shwetak","family":"Patel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4079-8275","authenticated-orcid":false,"given":"Yun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"Althoff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9279-5386","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7313-0082","authenticated-orcid":false,"given":"Daniel","family":"McDuff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5930-3899","authenticated-orcid":false,"given":"Xuhai Orson","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,21]]},"reference":[{"key":"11161_CR1","doi-asserted-by":"publisher","unstructured":"Cao, Y. et al. More than decision support: exploring patients\u2019 longitudinal usage of large language models in real-world healthcare-seeking journeys. In Proc. 2026 CHI Conference on Human Factors in Computing Systems (eds Oliver, N. et al.) https:\/\/doi.org\/10.1145\/3772318.3791946 (Association for Computing Machinery, 2026).","DOI":"10.1145\/3772318.3791946"},{"key":"11161_CR2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-67922-y","volume":"17","author":"MA Merrill","year":"2026","unstructured":"Merrill, M. A. et al. Transforming wearable data into personal health insights using large language model agents. Nat. Commun. 17, 1143 (2026).","journal-title":"Nat. Commun."},{"key":"11161_CR3","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1038\/s41746-018-0070-0","volume":"1","author":"SH Lee","year":"2018","unstructured":"Lee, S. H. Natural language generation for electronic health records. npj Digit. Med. 1, 63 (2018).","journal-title":"npj Digit. Med."},{"key":"11161_CR4","doi-asserted-by":"publisher","unstructured":"McDuff, D. et al. Towards accurate differential diagnosis with large language models. Nature 642, 451\u2013457 https:\/\/doi.org\/10.1038\/s41586-025-08869-4 (2025).","DOI":"10.1038\/s41586-025-08869-4"},{"key":"11161_CR5","doi-asserted-by":"publisher","first-page":"e2343689","DOI":"10.1001\/jamanetworkopen.2023.43689","volume":"6","author":"M Benary","year":"2023","unstructured":"Benary, M. et al. Leveraging large language models for decision support in personalized oncology. JAMA Netw. Open 6, e2343689 (2023).","journal-title":"JAMA Netw. Open"},{"key":"11161_CR6","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1038\/s41587-023-01789-6","volume":"41","author":"J-P Vert","year":"2023","unstructured":"Vert, J.-P. How will generative AI disrupt data science in drug discovery? Nat. Biotechnol. 41, 750\u2013751 (2023).","journal-title":"Nat. Biotechnol."},{"key":"11161_CR7","doi-asserted-by":"publisher","unstructured":"Gottweis, J. et al. Accelerating scientific discovery with Co-Scientist. Nature 655, 487\u2013496 https:\/\/doi.org\/10.1038\/s41586-026-10644-y (2026).","DOI":"10.1038\/s41586-026-10644-y"},{"key":"11161_CR8","doi-asserted-by":"publisher","unstructured":"Khasentino, J. et al. A personal health large language model for sleep and fitness coaching. Nat. Med. https:\/\/doi.org\/10.1038\/s41591-025-03888-0 (2025).","DOI":"10.1038\/s41591-025-03888-0"},{"key":"11161_CR9","doi-asserted-by":"publisher","unstructured":"Breda, J. et al. SymptomAI: towards a conversational AI agent for everyday symptom assessment. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2605.04012 (2026).","DOI":"10.48550\/arxiv.2605.04012"},{"key":"11161_CR10","unstructured":"WHOOP. Introducing whoop coach, powered by OpenAI. WHOOP https:\/\/www.whoop.com\/us\/en\/thelocker\/introducing-whoop-coach-powered-by-openai\/ (2023)."},{"key":"11161_CR11","unstructured":"Oura Team. Introducing Oura advisor: your AI-powered personal health companion. Oura https:\/\/ouraring.com\/blog\/oura-advisor\/ (2025)."},{"key":"11161_CR12","doi-asserted-by":"publisher","unstructured":"Tu, T. et al. Towards conversational diagnostic AI. Nature 642, 442\u2013450 https:\/\/doi.org\/10.1038\/s41586-025-08866-7 (2025).","DOI":"10.1038\/s41586-025-08866-7"},{"key":"11161_CR13","doi-asserted-by":"publisher","first-page":"2648","DOI":"10.1038\/s41591-024-03155-8","volume":"30","author":"NS Zheng","year":"2024","unstructured":"Zheng, N. S. et al. Sleep patterns and risk of chronic disease as measured by long-term monitoring with commercial wearable devices in the all of us research program. Nat. Med. 30, 2648\u20132656 (2024).","journal-title":"Nat. Med."},{"key":"11161_CR14","doi-asserted-by":"publisher","first-page":"e23954","DOI":"10.2196\/23954","volume":"22","author":"M Ringeval","year":"2020","unstructured":"Ringeval, M., Wagner, G., Denford, J., Par\u00e9, G. & Kitsiou, S. Fitbit-based interventions for healthy lifestyle outcomes: systematic review and meta-analysis. J. Med. Internet Res. 22, e23954 (2020).","journal-title":"J. Med. Internet Res."},{"key":"11161_CR15","doi-asserted-by":"publisher","first-page":"e12070","DOI":"10.2196\/12070","volume":"7","author":"J-W Kim","year":"2019","unstructured":"Kim, J.-W. et al. Impact of personal health records and wearables on health outcomes and patient response: three-arm randomized controlled trial. JMIR mHealth uHealth 7, e12070 (2019).","journal-title":"JMIR mHealth uHealth"},{"key":"11161_CR16","doi-asserted-by":"publisher","unstructured":"J\u00f6rke, M. et al. GPTCoach: towards LLM-based physical activity coaching. In Proc. 2025 CHI Conference on Human Factors in Computing Systems (eds Yamashita, N. et al) https:\/\/doi.org\/10.1145\/3706598.3713819 (Association for Computing Machinery, 2025).","DOI":"10.1145\/3706598.3713819"},{"key":"11161_CR17","doi-asserted-by":"crossref","unstructured":"J\u00f6rke, M. et al. Bloom: designing for LLM-augmented behavior change interactions. In Proc. 2026 CHI Conference on Human Factors in Computing Systems (eds Oliver, N. et al.) 1\u201327 (Association for Computing Machinery, 2026).","DOI":"10.1145\/3772318.3790506"},{"key":"11161_CR18","doi-asserted-by":"crossref","unstructured":"Merrill, M. A., Tan, M., Gupta, V., Hartvigsen, T. & Althoff, T. Language models still struggle to zero-shot reason about time series. In Findings of the Association for Computational Linguistics: EMNLP 2024 (eds Al-Onaizan, Y. et al.) 3512\u20133533 (Association for Computational Linguistics, 2024).","DOI":"10.18653\/v1\/2024.findings-emnlp.201"},{"key":"11161_CR19","unstructured":"Topol, E. Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again (Hachette, 2019)."},{"key":"11161_CR20","doi-asserted-by":"publisher","unstructured":"Srinivas, V. et al. Substance over style: evaluating proactive conversational coaching agents. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2503.19328 (2025).","DOI":"10.48550\/arxiv.2503.19328"},{"key":"11161_CR21","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1038\/s41591-023-02792-9","volume":"30","author":"G Graham","year":"2024","unstructured":"Graham, G., Goren, N., Sounderajah, V. & DeSalvo, K. Information is a determinant of health. Nat. Med. 30, 927\u2013928 (2024).","journal-title":"Nat. Med."},{"key":"11161_CR22","doi-asserted-by":"crossref","unstructured":"Basar, E., Hendrickx, I., Krahmer, E., Bruijn, G.-J. & Bosse, T. To what extent are large language models capable of generating substantial reflections for motivational interviewing counseling chatbots? A human evaluation. In Proc. 1st Human-Centered Large Language Modeling Workshop (eds Soni, N. et al.) 41\u201352 (Association for Computational Linguistics, 2024).","DOI":"10.18653\/v1\/2024.hucllm-1.4"},{"key":"11161_CR23","doi-asserted-by":"publisher","unstructured":"Wang, X. et al. Self-consistency improves chain of thought reasoning in language models. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2203.11171 (2022).","DOI":"10.48550\/arxiv.2203.11171"},{"key":"11161_CR24","doi-asserted-by":"crossref","unstructured":"Chen, J., Saha, S. & Bansal, M. ReConcile: round-table conference improves reasoning via consensus among diverse LLMs. In Proc. 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (eds Ku, L.-W. et al.) 7066\u20137085 (Association for Computational Linguistics, 2024).","DOI":"10.18653\/v1\/2024.acl-long.381"},{"key":"11161_CR25","doi-asserted-by":"crossref","unstructured":"Tang, X. et al. MedAgents: large language models as collaborators for zero-shot medical reasoning. In Findings of the Association for Computational Linguistics: ACL 2024 (eds Ku, L.-W. et al.) 599\u2013621 (Association for Computational Linguistics, 2024).","DOI":"10.18653\/v1\/2024.findings-acl.33"},{"key":"11161_CR26","doi-asserted-by":"publisher","unstructured":"Du, Y., Li, S., Torralba, A., Tenenbaum, J. B. & Mordatch, I. Improving factuality and reasoning in language models through multiagent debate. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2305.14325 (2023).","DOI":"10.48550\/arxiv.2305.14325"},{"key":"11161_CR27","doi-asserted-by":"publisher","first-page":"79410","DOI":"10.52202\/079017-2522","volume":"37","author":"Y Kim","year":"2024","unstructured":"Kim, Y. et al. MDAgents: an adaptive collaboration of LLMs for medical decision-making. Neural Inf. Process. Syst. 37, 79410\u201379452 (2024).","journal-title":"Neural Inf. Process. Syst."},{"key":"11161_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Y. et al. Benchmarking data science agents. In Proc. 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (eds Ku, L.-W. et al.) 5677\u20135700 (Association for Computational Linguistics, 2024).","DOI":"10.18653\/v1\/2024.acl-long.308"},{"key":"11161_CR29","doi-asserted-by":"publisher","unstructured":"Hong, S. et al. Data interpreter: an LLM agent for data science. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2402.18679 (2024).","DOI":"10.48550\/arxiv.2402.18679"},{"key":"11161_CR30","doi-asserted-by":"crossref","unstructured":"Gu, K. et al. BLADE: benchmarking language model agents for data-driven science. In Findings of the Association for Computational Linguistics: EMNLP 2024 (eds Al-Onaizan, Y. et al.) 13936\u201313971 (Association for Computational Linguistics, 2024).","DOI":"10.18653\/v1\/2024.findings-emnlp.815"},{"key":"11161_CR31","doi-asserted-by":"publisher","unstructured":"Zhang, D. et al. DataSciBench: an LLM agent benchmark for data science. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2502.13897 (2025).","DOI":"10.48550\/arxiv.2502.13897"},{"key":"11161_CR32","doi-asserted-by":"publisher","unstructured":"Cheng, L., Li, X. & Bing, L. Is GPT-4 a good data analyst? The 2023 Conference on Empirical Methods in Natural Language Processing (eds Bouamor, H. et al.) https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.637 (Association for Computational Linguistics, 2023).","DOI":"10.18653\/v1\/2023.findings-emnlp.637"},{"key":"11161_CR33","doi-asserted-by":"crossref","unstructured":"Yin, P. et al. Natural language to code generation in interactive data science notebooks. In Proc. 61st Annual Meeting of the Association for Computational Linguistics (eds Rogers, A. et al.) 126\u2013173 (Association for Computational Linguistics, 2023).","DOI":"10.18653\/v1\/2023.acl-long.9"},{"key":"11161_CR34","doi-asserted-by":"publisher","unstructured":"Wu, X. et al. DACO: towards application-driven and comprehensive data analysis via code generation. In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track (eds Globerson, A. et al.) https:\/\/doi.org\/10.52202\/079017-2878 (2024).","DOI":"10.52202\/079017-2878"},{"key":"11161_CR35","unstructured":"Hu, X. et al. InfiAgent-DABench: evaluating agents on data analysis tasks. In International Conference on Machine Learning (eds Salakhutdinov, R. et al.) 19544\u201319572 (PMLR, 2024)."},{"key":"11161_CR36","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":"11161_CR37","doi-asserted-by":"publisher","unstructured":"Nori, H. et al. Can generalist foundation models outcompete special-purpose tuning? Case study in medicine. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2311.16452 (2023).","DOI":"10.48550\/arxiv.2311.16452"},{"key":"11161_CR38","doi-asserted-by":"publisher","unstructured":"Nori, H. et al. From medprompt to o1: exploration of run-time strategies for medical challenge problems and beyond. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2411.03590 (2024).","DOI":"10.48550\/arxiv.2411.03590"},{"key":"11161_CR39","doi-asserted-by":"publisher","first-page":"e52097","DOI":"10.2196\/52097","volume":"25","author":"J Mercado","year":"2023","unstructured":"Mercado, J., Espinosa-Curiel, I. E. & Mart\u0131\u0301nez-Miranda, J. Embodied conversational agents providing motivational interviewing to improve health-related behaviors: scoping review. J. Med. Internet Res. 25, e52097 (2023).","journal-title":"J. Med. Internet Res."},{"key":"11161_CR40","doi-asserted-by":"publisher","unstructured":"J\u00f6rke, M. et al. Supporting physical activity behavior change with LLM-based conversational agents. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2405.06061 (2024).","DOI":"10.48550\/arxiv.2405.06061"},{"key":"11161_CR41","doi-asserted-by":"publisher","unstructured":"Mantena, S. et al. Fine-tuning large language models in behavioral psychology for scalable physical activity coaching. npj Cardiovasc. Health 2, 48 https:\/\/doi.org\/10.1038\/s44325-025-00083-5 (2025).","DOI":"10.1038\/s44325-025-00083-5"},{"key":"11161_CR42","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":"11161_CR43","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1038\/s41586-026-10179-2","volume":"652","author":"AA Metwally","year":"2026","unstructured":"Metwally, A. A. et al. Insulin resistance prediction from wearables and routine blood biomarkers. Nature 652, 451\u2013461 (2026).","journal-title":"Nature"},{"key":"11161_CR44","doi-asserted-by":"publisher","unstructured":"The Gemini Team. Gemini: a family of highly capable multimodal models. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2312.11805 (2023).","DOI":"10.48550\/arxiv.2312.11805"},{"key":"11161_CR45","doi-asserted-by":"publisher","unstructured":"Saab, K. et al. Capabilities of Gemini models in medicine. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2404.18416 (2024).","DOI":"10.48550\/arxiv.2404.18416"},{"key":"11161_CR46","doi-asserted-by":"publisher","unstructured":"Yang, L. et al. Advancing multimodal medical capabilities of Gemini. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2405.03162 (2024).","DOI":"10.48550\/arxiv.2405.03162"},{"key":"11161_CR47","doi-asserted-by":"publisher","unstructured":"Gu, K. et al. RADAR: benchmarking language models on imperfect tabular data. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2506.08249 (2025).","DOI":"10.48550\/arxiv.2506.08249"},{"key":"11161_CR48","doi-asserted-by":"publisher","first-page":"1564","DOI":"10.1056\/NEJMp2404691","volume":"391","author":"IS Kohane","year":"2024","unstructured":"Kohane, I. S. Compared with what? Measuring AI against the health care we have. N. Engl. J. Med. 391, 1564\u20131566 (2024).","journal-title":"N. Engl. J. Med."},{"key":"11161_CR49","unstructured":"Fitbit Community. Fitbit labs: testing new, experimental health and fitness capabilities in the Fitbit app. Fitbit https:\/\/community.fitbit.com\/t5\/The-Pulse-Fitbit-Community-Blog\/Fitbit-Labs-Testing-new-experimental-health-amp-fitness-capabilities-in-the\/ba-p\/5675311 (2024)."},{"key":"11161_CR50","doi-asserted-by":"publisher","unstructured":"Maguire, M. & Delahunt, B. Doing a thematic analysis: a practical, step-by-step guide for learning and teaching scholars. Zenodo https:\/\/doi.org\/10.5281\/ZENODO.5828312 (2017).","DOI":"10.5281\/ZENODO.5828312"},{"key":"11161_CR51","doi-asserted-by":"crossref","unstructured":"Fodor, J. A. The Modularity of Mind (Bradford Books, 1983).","DOI":"10.7551\/mitpress\/4737.001.0001"},{"key":"11161_CR52","doi-asserted-by":"publisher","unstructured":"Jun, E., Seo, A., Heer, J. & Just, R. Tisane: authoring statistical models via formal reasoning from conceptual and data relationships. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2201.02705 (2022).","DOI":"10.48550\/arxiv.2201.02705"},{"key":"11161_CR53","first-page":"66","volume":"26","author":"J Liu","year":"2020","unstructured":"Liu, J., Boukhelifa, N. & Eagan, J. R. Understanding the role of alternatives in data analysis practices. IEEE Trans. Vis. Comput. Graph. 26, 66\u201376 (2020).","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"11161_CR54","doi-asserted-by":"publisher","unstructured":"Gu, K. et al. How do data analysts respond to AI assistance? A Wizard-of-Oz study. In Proc. CHI Conference on Human Factors in Computing Systems https:\/\/doi.org\/10.1145\/3613904.3641891 (Association for Computing Machinery, 2024).","DOI":"10.1145\/3613904.3641891"},{"key":"11161_CR55","doi-asserted-by":"publisher","unstructured":"Jiang, J., Wang, F., Shen, J., Kim, S. & Kim, S. A survey on large language models for code generation. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2406.00515 (2024).","DOI":"10.48550\/arxiv.2406.00515"},{"key":"11161_CR56","doi-asserted-by":"publisher","unstructured":"Dibia, V. LIDA: a tool for automatic generation of grammar-agnostic visualizations and infographics using large language models. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2303.02927 (2023).","DOI":"10.48550\/arxiv.2303.02927"},{"key":"11161_CR57","doi-asserted-by":"publisher","unstructured":"Quoc, T. T., Minh, D. H., Thanh, T. Q. & Nguyen-Duc, A. An empirical study on self-correcting large language models for data science code generation. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2408.15658 (2024).","DOI":"10.48550\/arxiv.2408.15658"},{"key":"11161_CR58","unstructured":"Yao, S. et al. ReAct: synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR) (2023)."},{"key":"11161_CR59","unstructured":"Doran, G. T. There\u2019s a S.M.A.R.T. way to write management\u2019s goals and objectives. J. Manage. Rev. 70, 35\u201336 (1981)."},{"key":"11161_CR60","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1146\/annurev.clinpsy.1.102803.143833","volume":"1","author":"J Hettema","year":"2005","unstructured":"Hettema, J., Steele, J. & Miller, W. R. Motivational interviewing. Annu. Rev. Clin. Psychol. 1, 91\u2013111 (2005).","journal-title":"Annu. Rev. Clin. Psychol."},{"key":"11161_CR61","unstructured":"Wang, X. et al. Self-consistency improves chain of thought reasoning in language models. In The Eleventh International Conference on Learning Representations (2023)."},{"key":"11161_CR62","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1080\/00048402.2014.992447","volume":"93","author":"J Schaffer","year":"2015","unstructured":"Schaffer, J. What not to multiply without necessity. Australas. J. Philos. 93, 644\u2013664 (2015).","journal-title":"Australas. J. Philos."},{"key":"11161_CR63","doi-asserted-by":"publisher","unstructured":"Kim, Y. et al. Tiered agentic oversight: a hierarchical multi-agent system for AI safety in healthcare. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2506.12482 (2025).","DOI":"10.48550\/arxiv.2506.12482"},{"key":"11161_CR64","doi-asserted-by":"publisher","unstructured":"Madaan, A. et al. Self-refine: iterative refinement with self-feedback. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2303.17651 (2023).","DOI":"10.48550\/arxiv.2303.17651"},{"key":"11161_CR65","doi-asserted-by":"publisher","unstructured":"Kim, Y. et al. BehaviorSFT: behavioral token conditioning for clinical agents across the proactivity spectrum. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2505.21757 (2025).","DOI":"10.48550\/arxiv.2505.21757"},{"key":"11161_CR66","doi-asserted-by":"publisher","unstructured":"Liu, Y., Althoff, T. & Heer, J. Paths explored, paths omitted, paths obscured: decision points and selective reporting in end-to-end data analysis. In Proc. 2020 CHI Conference on Human Factors in Computing Systems (eds Bernhaupt, R. et al.) https:\/\/doi.org\/10.1145\/3313831.3376533 (Association for Computing Machinery, 2020).","DOI":"10.1145\/3313831.3376533"},{"key":"11161_CR67","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1177\/1745691616658637","volume":"11","author":"S Steegen","year":"2016","unstructured":"Steegen, S., Tuerlinckx, F., Gelman, A. & Vanpaemel, W. Increasing transparency through a multiverse analysis. Perspect. Psychol. Sci. 11, 702\u2013712 (2016).","journal-title":"Perspect. Psychol. Sci."},{"key":"11161_CR68","doi-asserted-by":"publisher","unstructured":"Zheng, L. et al. Judging LLM-as-a-judge with MT-bench and chatbot arena. Neural Inf. Process. Syst. https:\/\/doi.org\/10.52202\/075280-2020 (2023).","DOI":"10.52202\/075280-2020"},{"key":"11161_CR69","doi-asserted-by":"crossref","unstructured":"Chiang, C.-H. & Lee, H.-Y. Can large language models be an alternative to human evaluations? In Proc. 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (eds Rogers, A. et al.) 15607\u201315631 (Association for Computational Linguistics, 2023).","DOI":"10.18653\/v1\/2023.acl-long.870"},{"key":"11161_CR70","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1086\/266520","volume":"18","author":"E Bennett","year":"1954","unstructured":"Bennett, E., Alpert, R. & Goldstein, A. Communications through limited-response questioning. Public Opin. Q. 18, 303\u2013308 (1954).","journal-title":"Public Opin. Q."},{"key":"11161_CR71","doi-asserted-by":"publisher","unstructured":"Chen, M. et al. Evaluating large language models trained on code. Preprint at https:\/\/doi.org\/10.48550\/arxiv.2107.03374 (2021).","DOI":"10.48550\/arxiv.2107.03374"},{"key":"11161_CR72","unstructured":"StatPearls Publishing. American Board of Internal Medicine: endocrinology, diabetes, & metabolism exam. StatPearls https:\/\/www.statpearls.com\/boardreview\/Endocrinology (2024)."},{"key":"11161_CR73","unstructured":"BoardVitals. Cardiology board review. BoardVitals https:\/\/www.boardvitals.com\/cardiology-board-review\/ (2024)."},{"key":"11161_CR74","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1001\/jama.2023.8288","volume":"330","author":"Z Kanjee","year":"2023","unstructured":"Kanjee, Z., Crowe, B. & Rodman, A. Accuracy of a generative artificial intelligence model in a complex diagnostic challenge. JAMA 330, 78\u201380 (2023).","journal-title":"JAMA"},{"key":"11161_CR75","doi-asserted-by":"publisher","first-page":"900","DOI":"10.1038\/s41591-020-0842-3","volume":"26","author":"Y Liu","year":"2020","unstructured":"Liu, Y. et al. A deep learning system for differential diagnosis of skin diseases. Nat. Med. 26, 900\u2013908 (2020).","journal-title":"Nat. Med."},{"key":"11161_CR76","doi-asserted-by":"crossref","unstructured":"Mallinar, N. et al. A scalable framework for evaluating health language models. npj Digit. Med. 9, 437 (2026).","DOI":"10.1038\/s41746-026-02492-x"},{"key":"11161_CR77","doi-asserted-by":"publisher","unstructured":"Holmes, S. et al. Usability testing of a healthcare chatbot: can we use conventional methods to assess conversational user interfaces? In Proc. 31st European Conference on Cognitive Ergonomics (eds Mulvenna, M. & Bond, R.) https:\/\/doi.org\/10.1145\/3335082.3335094 (Association for Computing Machinery, 2019).","DOI":"10.1145\/3335082.3335094"},{"key":"11161_CR78","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1002\/cpp.658","volume":"17","author":"T Munder","year":"2010","unstructured":"Munder, T., Wilmers, F., Leonhart, R., Linster, H. W. & Barth, J. Working Alliance inventory-short revised (WAI-SR): psychometric properties in outpatients and inpatients. Clin. Psychol. Psychother. 17, 231\u2013239 (2010).","journal-title":"Clin. Psychol. Psychother."},{"key":"11161_CR79","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1016\/j.jsat.2012.08.015","volume":"44","author":"MB Madson","year":"2013","unstructured":"Madson, M. B. et al. Measuring client perceptions of motivational interviewing: factor analysis of the client evaluation of motivational interviewing scale. J. Subst. Abuse Treat. 44, 330\u2013335 (2013).","journal-title":"J. Subst. Abuse Treat."},{"key":"11161_CR80","first-page":"65","volume":"6","author":"S Holm","year":"1979","unstructured":"Holm, S. A simple sequentially rejective multiple test procedure. Scand. J. Stat. 6, 65\u201370 (1979).","journal-title":"Scand. J. Stat."}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41586-026-11161-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-026-11161-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-026-11161-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,8]],"date-time":"2026-11-08T11:02:42Z","timestamp":1794135762000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41586-026-11161-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,21]]},"references-count":80,"journal-issue":{"issue":"8139","published-print":{"date-parts":[[2026,11,5]]}},"alternative-id":["11161"],"URL":"https:\/\/doi.org\/10.1038\/s41586-026-11161-8","relation":{},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,21]]},"assertion":[{"value":"22 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A.A.H., H.Y., Q.H., H.P., N.H., A.A.M., B.W., Y.K., Y.Y., J.G., S.S., A.A.L., J.V., I.R.G.-L., E.S., A.B., J.P., J.S., J.H., A.Z.F., J.L.P., C.H., Y.L., J.Z., M.M., S.P., T.A., X.L., D.M. and X.O.X. are current or former employees of Alphabet and may own stock as part of the standard compensation. X.O.X. is a tenure-track faculty member at Columbia University. The other authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}]}}