{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T19:30:58Z","timestamp":1775071858490,"version":"3.50.1"},"reference-count":72,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"14","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2345579"],"award-info":[{"award-number":["2345579"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Schmidt Sciences","award":["Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship"],"award-info":[{"award-number":["Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship"]}]}],"content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Adv."],"published-print":{"date-parts":[[2026,4,3]]},"abstract":"<jats:p>Electron microscopy (EM) reveals atomic-scale structures that underpin catalysis, energy storage, and semiconductor reliability, yet current workflows remain fragmented across segmentation, crystallographic reconstruction, property modeling, and literature review, often requiring weeks of expert effort. Although recent artificial intelligence models have assisted individual steps, the diversity of EM modalities and tasks means existing approaches remain siloed and perform poorly in complex multistage workflows. We present EMSeek, a modular, provenance-tracked multiagent platform that connects EM to materials insight through five key units: reference-guided one-for-all segmentation, mask-aware reconstruction of crystal structures from EM data, a gated mixture of experts property predictor with uncertainty calibration, literature retrieval with citation anchoring, and physical consistency checks with audit-ready reporting. These units are orchestrated by large language models (LLMs) that automatically plan, invoke, and execute tools, minimizing human intervention. On 20 material systems and five tasks, EMSeek delivers segmentation about twice as fast as Segment Anything with higher accuracy, achieves more than 90% structural similarity on STEM2Mat, and, with about 2% labeled calibration, matches or surpasses strong single experts on three out-of-distribution property benchmarks. A complete query runs in 2 to 5 minutes per image, roughly 50 times faster than expert workflows. Case studies on two-dimensional lattices and nanoparticles validate EMSeek\u2019s ability to automate complex workflows, with integrated uncertainty calibration and audit signals that provide scientists with rigorous yet actionable guidance to accelerate materials discovery.<\/jats:p>","DOI":"10.1126\/sciadv.aed0583","type":"journal-article","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:58:42Z","timestamp":1775066322000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":0,"title":["Bridging electron microscopy and materials analysis with an autonomous agentic platform"],"prefix":"10.1126","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7255-2109","authenticated-orcid":true,"given":"Guangyao","family":"Chen","sequence":"first","affiliation":[{"name":"College of Engineering, Cornell University, Ithaca, NY 14853, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5638-2106","authenticated-orcid":true,"given":"Wenhao","family":"Yuan","sequence":"additional","affiliation":[{"name":"College of Engineering, Cornell University, Ithaca, NY 14853, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9609-4299","authenticated-orcid":true,"given":"Fengqi","family":"You","sequence":"additional","affiliation":[{"name":"College of Engineering, Cornell University, Ithaca, NY 14853, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1038\/nmat4852"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.2c10687"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03049-y"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-022-04736-8"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/382144a0"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1038\/1831001a0"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1038\/189564a0"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41563-021-01050-y"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-12320-4"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04377-3"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tibs.2014.10.005"},{"key":"e_1_3_2_13_2","unstructured":"G. Chen S. Dong Y. Shu G. Zhang J. Sesay B. Karlsson J. Fu Y. Shi \u201cAutoAgents: A framework for automatic agent generation \u201d in Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (International Joint Conferences on Artificial Intelligence Organization 2024) pp. 22\u201330."},{"key":"e_1_3_2_14_2","unstructured":"T. Guo X. Chen Y. Wang R. Chang S. Pei N. V. Chawla O. Wiest X. Zhang \u201cLarge language model based multi-agents: A survey of progress and challenges \u201d in Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (International Joint Conferences on Artificial Intelligence Organization 2024) pp. 8048\u20138057."},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aaz8867"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-45569-5"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1038\/s44160-022-00231-0"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06734-w"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2414074122"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.01.021"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-19597-w"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2442-2"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1900548116"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1165620"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00555-8"},{"key":"e_1_3_2_26_2","unstructured":"Y. Yang Y. Tang Y. Chen X. Chen J. Qiu H. Xiong H. Yin Z. Luo Y. Zhang S. Tao W. Li Q. Zhang Y. Li W. Ouyang B. Zhao X. Wang F. Wei AutoMat: Enabling automated crystal structure reconstruction from microscopy via agentic tool use. arXiv:2505.12650 [cs.CV] (2025)."},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-024-02580-4"},{"key":"e_1_3_2_28_2","first-page":"021002","article-title":"Nonlocal effective electromagnetic wave characteristics of composite media: Beyond the quasistatic regime","volume":"11","author":"Torquato S.","year":"2021","unstructured":"S. Torquato, J. Kim, Nonlocal effective electromagnetic wave characteristics of composite media: Beyond the quasistatic regime. Phys. Rev. X 11, 021002 (2021).","journal-title":"Phys. Rev. X"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-022-00720-y"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-84499-w"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-023-01042-3"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-022-00949-7"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-020-00363-x"},{"key":"e_1_3_2_34_2","unstructured":"Z. Zhou M. M. Rahman Siddiquee N. Tajbakhsh J. Liang \u201cUNet++: A nested U-Net architecture for medical image segmentation \u201d in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support vol. 11045 of Lecture Notes in Computer Science D. Stoyanov Z. Taylor G. Carneiro T. Syeda-Mahmood A. Martel L. Maier-Hein J. M. R. S. Tavares A. Bradley J. P. Papa V. Belagiannis J. C. Nascimento Z. Lu S. Conjeti M. Moradi H. Greenspan A. Madabhushi Eds. (Springer International Publishing 2018) pp. 3\u201311."},{"key":"e_1_3_2_35_2","doi-asserted-by":"crossref","unstructured":"O. Ronneberger P. Fischer T. Brox \u201cU-Net: Convolutional networks for biomedical image segmentation \u201d in Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015 vol. 9351 of Lecture Notes in Computer Science N. Navab J. Hornegger W. M. Wells A. F. Frangi Eds. (Springer International Publishing 2015) pp. 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_36_2","unstructured":"B. M. Wood M. Dzamba X. Fu M. Gao M. Shuaibi L. Barroso-Luque K. Abdelmaqsoud V. Gharakhanyan J. R. Kitchin D. S. Levine K. Michel A. Sriram T. Cohen A. Das A. Rizvi S. J. Sahoo Z. W. Ulissi C. L. Zitnick UMA: A family of universal models for atoms. arXiv:2506.23971 [cs.LG] (2025)."},{"key":"e_1_3_2_37_2","unstructured":"B. Rhodes S. Vandenhaute V. \u0160imkus J. Gin J. Godwin T. Duignan M. Neumann Orb-v3: Atomistic simulation at scale. arXiv:2504.06231 [cond-mat.mtrl-sci] (2025)."},{"key":"e_1_3_2_38_2","doi-asserted-by":"crossref","unstructured":"I. Batatia P. Benner Y. Chiang A. M. Elena D. P. Kov\u00e1cs J. Riebesell X. R. Advincula M. Asta M. Avaylon W. J. Baldwin F. Berger N. Bernstein A. Bhowmik S. M. Blau V. C\u0103rare J. P. Darby S. De F. D. Pia V. L. Deringer R. Elijo\u0161ius Z. El-Machachi F. Falcioni E. Fako A. C. Ferrari A. Genreith-Schriever J. George R. E. A. Goodall C. P. Grey P. Grigorev S. Han W. Handley H. H. Heenen K. Hermansson C. Holm J. Jaafar S. Hofmann K. S. Jakob H. Jung V. Kapil A. D. Kaplan N. Karimitari J. R. Kermode N. Kroupa J. Kullgren M. C. Kuner D. Kuryla G. Liepuoniute J. T. Margraf I.-B. Magd\u0103u A. Michaelides J. H. Moore A. A. Naik S. P. Niblett S. W. Norwood N. O\u2019Neill C. Ortner K. A. Persson K. Reuter A. S. Rosen L. L. Schaaf C. Schran B. X. Shi E. Sivonxay T. K. Stenczel V. Svahn C. Sutton T. D. Swinburne J. Tilly C. van der Oord E. Varga-Umbrich T. Vegge M. Vondr\u00e1k Y. Wang W. C. Witt F. Zills G. Cs\u00e1nyi A foundation model for atomistic materials chemistry. arXiv:2401.00096 [physics.chem-ph] (2024).","DOI":"10.1063\/5.0297006"},{"key":"e_1_3_2_39_2","unstructured":"H. Yang C. Hu Y. Zhou X. Liu Y. Shi J. Li G. Li Z. Chen S. Chen C. Zeni M. Horton R. Pinsler A. Fowler D. Z\u00fcgner T. Xie J. Smith L. Sun Q. Wang L. Kong C. Liu H. Hao Z. Lu MatterSim: A deep learning atomistic model across elements temperatures and pressures. arXiv:2405.04967 [cond-mat.mtrl-sci] (2024)."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1088\/2053-1583\/aacfc1"},{"key":"e_1_3_2_41_2","unstructured":"LeMaterial LeMat-Bulk version a36d6af Hugging Face (2024); https:\/\/doi.org\/10.57967\/HF\/3762."},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-01055-1"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-017-02047-5"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1038\/nnano.2012.193"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1093\/mam\/ozae044.211"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-19697-1"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-018-0093-8"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-58160-3"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.3390\/nano14201614"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-023-01163-9"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42004-024-01393-y"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1038\/s44334-024-00003-y"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.1c12466"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-025-01800-5"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1093\/micmic\/ozae001"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.micron.2019.02.009"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrp.2022.100876"},{"key":"e_1_3_2_58_2","unstructured":"S. Narayanan J. D. Braza R.-R. Griffiths M. Ponnapati A. Bou J. M. Laurent O. Kabeli G. Wellawatte S. Cox S. G. Rodriques A. White \u201cAviary: Training language agents on challenging scientific tasks\u201d (2025); https:\/\/openreview.net\/forum?id=25Grz6oh7d."},{"key":"e_1_3_2_59_2","unstructured":"M. D. Skarlinski S. Cox J. M. Laurent J. D. Braza M. Hinks M. J. Hammerling M. Ponnapati S. G. Rodriques A. D. White Language agents achieve superhuman synthesis of scientific knowledge. arXiv:2409.13740 [cs.CL] (2024)."},{"key":"e_1_3_2_60_2","unstructured":"J. L\u00e1la O. O\u2019Donoghue A. Shtedritski S. Cox S. G. Rodriques A. D. White PaperQA: Retrieval-Augmented Generative agent for scientific research. arXiv:2312.07559 [cs.CL] (2023)."},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1021\/acsenergylett.6b00093"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aas9311"},{"key":"e_1_3_2_63_2","doi-asserted-by":"crossref","unstructured":"W. W. Wright \u201cMaterials science and engineering. An introduction (2nd edition) \u201d in Polymer International W. D. Callister Jr (John Wiley & Sons 1993) pp. 282\u2013283.","DOI":"10.1002\/pi.4990300228"},{"key":"e_1_3_2_64_2","unstructured":"A. Eldeeb Metallurgy and materials science knowledge extraction dataset (2024); https:\/\/huggingface.co\/datasets\/AbdulrhmanEldeeb\/metallurgy-qa."},{"key":"e_1_3_2_65_2","unstructured":"F. De La Pe\u00f1a T. Ostasevicius V. T. Fauske P. Burdet P. Jokubauskas M. Nord E. Prestat M. Sarahan K. E. MacArthur D. N. Johnstone J. Taillon J. Caron T. Furnival A. Eljarrat S. Mazzucco V. Migunov T. Aarholt M. Walls F. Winkler B. Martineau G. Donval E. R. Hoglund I. Alxneit I. Hjorth L. F. Zagonel A. Garmannslund C. Gohlke I. Iyengar Huang-Wei Chang hyperspy\/hyperspy: HyperSpy 1.3 version v1.3 Zenodo (2017); https:\/\/doi.org\/10.5281\/ZENODO.583693."},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1017\/S1431927621000477"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40679-017-0042-5"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.453"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2012.10.028"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41563-025-02272-0"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1039\/D5DT02255J"},{"key":"e_1_3_2_72_2","unstructured":"T. V. Rajan C. P. Sharma A. Sharma Heat Treatment: Principles and Techniques (PHI Learning Private Limited New Delhi India 2nd ed. 2011)."},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms5673"}],"container-title":["Science Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/sciadv.aed0583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:58:54Z","timestamp":1775066334000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/sciadv.aed0583"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,3]]},"references-count":72,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2026,4,3]]}},"alternative-id":["10.1126\/sciadv.aed0583"],"URL":"https:\/\/doi.org\/10.1126\/sciadv.aed0583","relation":{},"ISSN":["2375-2548"],"issn-type":[{"value":"2375-2548","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,3]]},"assertion":[{"value":"2025-10-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eaed0583"}}