{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T05:09:18Z","timestamp":1789016958632,"version":"build-2803163510"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T00:00:00Z","timestamp":1788998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Nutr."],"abstract":"<jats:p>\n                    Animal-source foods are nutritionally \u201cplastic,\u201d with fatty acid profiles, vitamins, and minerals that can be altered by animal diets and management. Although the literature documenting these effects is extensive, it is fragmented across disciplines and experimental contexts, limiting translation into actionable guidance for food quality and human nutrition. We developed the Intelligent System for Integrating Global Human &amp;amp; Animal Health Technology (INSIGHT), a domain-specialized retrieval-augmented generation (RAG) system designed to synthesize evidence across animal production and human nutrition research with explicit provenance. INSIGHT employs a nine-stage RAG pipeline that integrates query expansion, hybrid retrieval, evidence reranking, and self-verification to deliver transparent, citation-linked responses. Throughout, retrieval refers to document selection, integration to the combination of retrieved evidence into a coherent evidence set, and synthesis to the LLM-based generation of grounded narrative responses. The knowledge base comprises ~4,000 peer-reviewed papers in animal science, feed composition, and human dietary research. To evaluate retrieval performance across diverse literature contexts, we developed a multi-group evaluation framework: 282 documents were randomly selected and organized into 26 semantically coherent groups of ~10 papers each. For each group, Perplexity Deep Research generated 25 question\u2013answer pairs and identified ground-truth relevant documents. Each question was posed to INSIGHT, yielding document-level precision, recall, and F1-score metrics across 614 total queries. Generalized linear mixed models with beta regression revealed significant between-group performance variation (\n                    <jats:italic>p<\/jats:italic>\n                    \u202f&amp;lt;\u202f0.0001), indicating that retrieval effectiveness depends on semantic domain characteristics. Across groups, INSIGHT achieved a mean precision of 0.77 (SD\u202f=\u202f0.12), recall of 0.62 (SD\u202f=\u202f0.15), and F1-score of 0.67 (SD\u202f=\u202f0.10), all significantly exceeding a 0.5 baseline (\n                    <jats:italic>p<\/jats:italic>\n                    \u202f&amp;lt;\u202f0.0001). These results demonstrate that INSIGHT provides reliable document-level retrieval across diverse topical domains, though significant between-group performance variation (\n                    <jats:italic>p<\/jats:italic>\n                    \u202f&amp;lt;\u202f0.0001) indicates that retrieval effectiveness is context-dependent. The present evaluation is intentionally scoped as a controlled retrieval performance assessment; end-to-end synthesis quality evaluation using systematic review benchmarking and RAG assessment metrics represents a critical next step. Domain-specialized, evidence-grounded systems such as INSIGHT can accelerate cross-disciplinary knowledge integration, with continued development focused on improving recall in semantically complex domains, enhancing terminology normalization, and expanding corpus coverage across animal production and human nutrition research.\n                  <\/jats:p>","DOI":"10.3389\/fnut.2026.1815038","type":"journal-article","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T04:32:02Z","timestamp":1789014722000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Toward an integrated animal\u2013human nutrition intelligence via agentic retrieval-augmented language models"],"prefix":"10.3389","volume":"13","author":[{"given":"Luis O.","family":"Tedeschi","sequence":"first","affiliation":[{"name":"Department of Animal Science, Texas A&M University, College Station","place":["TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicole","family":"Greer","sequence":"additional","affiliation":[{"name":"Department of Animal Science, Texas A&M University, College Station","place":["TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karun","family":"Kaniyamattam","sequence":"additional","affiliation":[{"name":"Department of Animal Science, Texas A&M University, College Station","place":["TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dheeraj","family":"Mudireddy","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Texas A&M Institute of Data Science, Texas A&M University, College Station","place":["TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Strong","sequence":"additional","affiliation":[{"name":"Department of Agricultural Leadership, Education & Communications, Texas A&M University, College Station","place":["TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Praneet Sai Madhu","family":"Surabhi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Texas A&M Institute of Data Science, Texas A&M University, College Station","place":["TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Tao","sequence":"additional","affiliation":[{"name":"College of Performance, Visualization & Fine Arts, Department of Electrical & Computer Engineering, Texas A&M Institute of Data Science, Texas A&M University, College Station","place":["TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ashley","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Public Health, Texas A&M University, College Station","place":["TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1424912","DOI":"10.3389\/fnut.2024.1424912","article-title":"Nutritional importance of animal-sourced foods in a healthy diet","volume":"11","author":"Sheffield","year":"2024","journal-title":"Front Nutr"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"3346","DOI":"10.3390\/nu16193346","article-title":"Unveiling the nutritional quality of terrestrial animal source foods by species and characteristics of livestock systems","volume":"16","author":"Rueda Garc\u00eda","year":"2024","journal-title":"Nutrients"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/1475-2891-9-10","article-title":"A review of fatty acid profiles and antioxidant content in grass-fed and grain-fed beef","volume":"9","author":"Daley","year":"2010","journal-title":"Nutr J"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"18","DOI":"10.5851\/kosfa.2021.e73","article-title":"Fatty acid composition of grain- and grass-fed beef and their nutritional value and health implication","volume":"42","author":"Nogoy","year":"2022","journal-title":"Food Sci Anim Resources"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/j.meatsci.2013.08.010","article-title":"Impact of grass\/forage feeding versus grain finishing on beef nutrients and sensory quality: the U.S. experience","volume":"96","author":"Van Elswyk","year":"2014","journal-title":"Meat Sci"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1186\/s40104-015-0025-0","article-title":"Challenges in enriching milk fat with polyunsaturated fatty acids","volume":"6","author":"Lanier","year":"2015","journal-title":"J Anim Sci Biotechnol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.1007\/s11745-004-1348-6","article-title":"Modifying milk fat composition of dairy cows to enhance fatty acids beneficial to human health","volume":"39","author":"Lock","year":"2004","journal-title":"Lipids"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"38","DOI":"10.3390\/ruminants5030038","article-title":"Milk fat depression in dairy cattle: etiology, prevention, and recovery approaches","volume":"5","author":"Mart\u00ednez","year":"2025","journal-title":"Ruminants"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"955846","DOI":"10.3389\/fnut.2022.955846","article-title":"Producing natural functional and low-carbon milk by regulating the diet of the cattle-the fatty acid associated rumen fermentation, biohydrogenation, and microorganism response","volume":"9","author":"Sun","year":"2022","journal-title":"Front Nutr"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"2047","DOI":"10.1016\/j.jacc.2011.06.063","article-title":"Omega-3 fatty acids and cardiovascular disease: effects on risk factors, molecular pathways, and clinical events","volume":"58","author":"Mozaffarian","year":"2011","journal-title":"J Am Coll Cardiol"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"7655","DOI":"10.3168\/jds.2019-17662","article-title":"Invited review: role of rumen biohydrogenation intermediates and rumen microbes in diet-induced milk fat depression: an update","volume":"103","author":"Dewanckele","year":"2020","journal-title":"J Dairy Sci"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"10122","DOI":"10.3390\/molecules180910122","article-title":"Variation of vitamin D in cow's milk and interaction with \u03b2-lactoglobulin","volume":"18","author":"Bulgari","year":"2013","journal-title":"Molecules"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"3545","DOI":"10.3168\/jds.2017-13824","article-title":"Effect of dietary vitamin D3 and 25-hydroxyvitamin D3 supplementation on plasma and milk 25-hydroxyvitamin D3 concentration in dairy cows","volume":"101","author":"Guo","year":"2018","journal-title":"J Dairy Sci"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.3945\/ajcn.115.120873","article-title":"Vitamin D deficiency in Europe: pandemic?","volume":"103","author":"Cashman","year":"2016","journal-title":"Am J Clin Nutr"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1427","DOI":"10.1017\/s1751731112000225","article-title":"Reevaluation of vitamin E supplementation of dairy cows: bioavailability, animal health and milk quality","volume":"6","author":"Politis","year":"2012","journal-title":"Animal"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1111\/j.1439-0442.2007.00999.x","article-title":"Somatic cell count in milk of selenium-supplemented dairy cows after an intramammary challenge with Staphylococcus aureus","volume":"54","author":"Kruze","year":"2007","journal-title":"J Vet Med A Physiol Pathol Clin Med"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"545","DOI":"10.3390\/molecules21040545","article-title":"Selenium in cattle: a review","volume":"21","author":"Mehdi","year":"2016","journal-title":"Molecules"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"3365","DOI":"10.2527\/1999.77123365x","article-title":"Effect of selenate as a feed supplement to dairy cows in comparison to selenite and selenium yeast","volume":"77","author":"Ortman","year":"1999","journal-title":"J Anim Sci"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1256","DOI":"10.1016\/S0140-6736(11)61452-9","article-title":"Selenium and human health","volume":"379","author":"Rayman","year":"2012","journal-title":"Lancet"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1111\/j.1439-0396.2008.00913.x","article-title":"Effect of dietary chromium supplementation on productive and reproductive performance of early lactating dairy cows under heat stress","volume":"94","author":"Soltan","year":"2010","journal-title":"J Anim Physiol Anim Nutr (Berl)"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"65","DOI":"10.15232\/aas.2024-02653","article-title":"Review: history of chromium in animal nutrition in the United States","volume":"41","author":"Spears","year":"2025","journal-title":"Appl Anim Sci"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"txaa146","DOI":"10.1093\/tas\/txaa146","article-title":"Chromium propionate supplementation alters animal growth performance, carcass characteristics, and skeletal muscle properties in feedlot steers","volume":"4","author":"Baggerman","year":"2020","journal-title":"Transl Anim Sci"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"217","DOI":"10.2527\/jas.2015-9517","article-title":"Effects of chromium supplementation to feedlot steers on growth performance, insulin sensitivity, and carcass characteristics","volume":"94","author":"Kneeskern","year":"2016","journal-title":"J Anim Sci"},{"key":"ref24","author":"Liao","year":"2025"},{"key":"ref25","author":"Thudumu","year":"2026"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"e012545","DOI":"10.1136\/bmjopen-2016-012545","article-title":"Analysis of the time and workers needed to conduct systematic reviews of medical interventions using data from the PROSPERO registry","volume":"7","author":"Borah","year":"2017","journal-title":"BMJ Open"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"100443","DOI":"10.1016\/j.conctc.2019.100443","article-title":"The significant cost of systematic reviews and meta-analyses: a call for greater involvement of machine learning to assess the promise of clinical trials","volume":"16","author":"Michelson","year":"2019","journal-title":"Contemp Clin Trials Commun"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"e2404328121","DOI":"10.1073\/pnas.2404328121","article-title":"ChatGPT as research scientist: probing GPT\u2019S capabilities as a research librarian, research ethicist, data generator, and data predictor","volume":"121","author":"Lehr","year":"2024","journal-title":"Proc Natl Acad Sci"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3703155","article-title":"A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions","volume":"43","author":"Huang","year":"2025","journal-title":"ACM Trans Inf Syst"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"23","DOI":"10.3390\/nu18010023","article-title":"Large language models for real-world nutrition assessment: structured prompts, multi-model validation and expert oversight","volume":"18","author":"Ase","year":"2026","journal-title":"Nutrients"},{"key":"ref31","author":"Lee","year":"2025"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"856","DOI":"10.3390\/math13050856","article-title":"Hallucination mitigation for retrieval-augmented large language models: a review","volume":"13","author":"Zhang","year":"2025","journal-title":"Mathematics (Basel)"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1093\/jas\/skaf445","article-title":"ASAS-NANP symposium: mathematical modeling in animal nutrition: the evolution of large language models and their impact on animal sciences","volume":"104","author":"Tedeschi","year":"2026","journal-title":"J Anim Sci"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"e0000758","DOI":"10.1371\/journal.pdig.0000758","article-title":"AI-driven personalized nutrition: RAG-based digital health solution for obesity and type 2 diabetes","volume":"4","author":"Gavai","year":"2025","journal-title":"PLOS Digit Health"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"bbac409","DOI":"10.1093\/bib\/bbac409","article-title":"BioGPT: generative pre-trained transformer for biomedical text generation and mining","volume":"23","author":"Luo","year":"2022","journal-title":"Brief Bioinform"},{"key":"ref36","author":"Bolton","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1038\/s41746-022-00742-2","article-title":"A large language model for electronic health records","volume":"5","author":"Yang","year":"2022","journal-title":"NPJ Digit Med"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1038\/s41586-025-10072-4","article-title":"Synthesizing scientific literature with retrieval-augmented language models","volume":"650","author":"Asai","year":"2026","journal-title":"Nature"},{"key":"ref39","author":"Wu","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1038\/s41746-025-01533-1","article-title":"Medical foundation large language models for comprehensive text analysis and beyond","volume":"8","author":"Xie","year":"2025","journal-title":"npj Digit Med"},{"key":"ref41","author":"Kerner","year":"2024"},{"key":"ref42","author":"Lewis","year":"2021"},{"key":"ref43","author":"Grattafiori","year":"2024"},{"key":"ref44","author":"Mesnard","year":"2024"},{"key":"ref45","author":"Asai","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of hallucination in natural language generation","volume":"55","author":"Ji","year":"2023","journal-title":"ACM Comput Surv"},{"key":"ref47","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1109\/SDS66131.2025.00029","article-title":"Efficient and reproducible biomedical question answering using retrieval augmented generation","volume-title":"2025 IEEE Swiss Conference on Data Science (SDS)","author":"Stuhlmann","year":"2025"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1016\/j.agsy.2005.11.004","article-title":"Assessment of the adequacy of mathematical models","volume":"89","author":"Tedeschi","year":"2006","journal-title":"Agric Syst"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1037\/1082-989X.11.1.54","article-title":"A better lemon squeezer? Maximum-likelihood regression with beta-distributed dependent variables","volume":"11","author":"Smithson","year":"2006","journal-title":"Psychol Methods"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"105965","DOI":"10.1016\/j.compag.2020.105965","article-title":"AGROVOC: the linked data concept hub for food and agriculture","volume":"196","author":"Subirats-Coll","year":"2022","journal-title":"Comput Electron Agric"},{"key":"ref51","author":"Edge","year":"2025"},{"key":"ref52","author":"Wu","year":"2023"},{"key":"ref53","first-page":"150","volume-title":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations","author":"Es","year":"2024"}],"container-title":["Frontiers in Nutrition"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1815038\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T04:32:08Z","timestamp":1789014728000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1815038\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,10]]},"references-count":53,"alternative-id":["10.3389\/fnut.2026.1815038"],"URL":"https:\/\/doi.org\/10.3389\/fnut.2026.1815038","relation":{},"ISSN":["2296-861X"],"issn-type":[{"value":"2296-861X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,10]]},"article-number":"1815038"}}