{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T19:27:29Z","timestamp":1787686049318,"version":"build-2784847793"},"reference-count":66,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T00:00:00Z","timestamp":1781913600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000015","name":"US Department of Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Reliability Engineering & System Safety"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.ress.2026.113057","type":"journal-article","created":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T15:09:54Z","timestamp":1781968194000},"page":"113057","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"P2","title":["A retrieval-augmented, domain-intelligent agentic framework for reliable decision support in safety-critical nuclear engineering"],"prefix":"10.1016","volume":"277","author":[{"given":"Zavier Ndum","family":"Ndum","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Ford","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mansung","family":"Yim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1337-2527","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ress.2026.113057_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2025.112123","article-title":"AutoGraph: An intelligent knowledge-graph agent for procedure automation and dynamic human reliability support in high-risk industries","volume":"270","author":"Xiao","year":"2026","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.113057_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2026.112277","article-title":"A deep learning framework for aviation risk classification and high-order coupled risk modeling","volume":"271","author":"Li","year":"2026","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.113057_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2026.112333","article-title":"A hybrid deep learning and large language models framework for ship collision accident analysis","volume":"273","author":"Zhang","year":"2026","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.113057_b4","series-title":"A comprehensive survey of scientific large language models and their applications in scientific discovery","author":"Zhang","year":"2024"},{"key":"10.1016\/j.ress.2026.113057_b5","series-title":"A survey of large language models","author":"Zhao","year":"2023"},{"key":"10.1016\/j.ress.2026.113057_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2021.107636","article-title":"Uncertainty quantification for multiphase-CFD simulations of bubbly flows: A machine learning-based Bayesian approach supported by high-resolution experiments","volume":"212","author":"Liu","year":"2021","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.113057_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2025.111353","article-title":"Bayesian optimized deep ensemble for uncertainty quantification of deep neural networks: A system safety case study on sodium fast reactor thermal stratification modeling","volume":"264","author":"Abulawi","year":"2025","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.113057_b8","article-title":"An AI-driven thermal-fluid testbed for advanced small modular reactors: Integration of digital twin and large language models","volume":"4","author":"Lim","year":"2025","journal-title":"AI Therm Fluids"},{"key":"10.1016\/j.ress.2026.113057_b9","doi-asserted-by":"crossref","DOI":"10.2196\/63400","article-title":"Perceptions and earliest experiences of medical students and faculty with ChatGPT in medical education: Qualitative study","volume":"11","author":"Abouammoh","year":"2025","journal-title":"JMIR Med Educ"},{"key":"10.1016\/j.ress.2026.113057_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.esr.2024.101632","article-title":"Advanced nuclear technologies in modern energy systems: A comparative risk assessment in Japan","volume":"57","author":"Koo","year":"2025","journal-title":"Energy Strat Rev"},{"key":"10.1016\/j.ress.2026.113057_b11","series-title":"The NEA small modular reactor dashboard","author":"Nuclear Energy Agency (NEA)","year":"2025"},{"key":"10.1016\/j.ress.2026.113057_b12","series-title":"Application of framework for integrating safety, security and safeguards (3Ss) into the design of used nuclear fuel storage facility","author":"Badwan","year":"2015"},{"key":"10.1016\/j.ress.2026.113057_b13","first-page":"175","article-title":"Workflows using mantid","volume":"vol. 1315","author":"Godoy","year":"2020"},{"key":"10.1016\/j.ress.2026.113057_b14","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/j.jcp.2016.02.043","article-title":"Modeling and simulation challenges pursued by the consortium for Advanced Simulation of Light Water Reactors (CASL)","volume":"313","author":"Turinsky","year":"2016","journal-title":"J Comput Phys"},{"key":"10.1016\/j.ress.2026.113057_b15","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1016\/j.jcp.2016.09.003","article-title":"The virtual environment for reactor applications (VERA): Design and architecture","volume":"326","author":"Turner","year":"2016","journal-title":"J Comput Phys"},{"key":"10.1016\/j.ress.2026.113057_b16","doi-asserted-by":"crossref","DOI":"10.2196\/72998","article-title":"Citation accuracy challenges posed by large language models","volume":"11","author":"Zhang","year":"2025","journal-title":"JMIR Med Educ"},{"key":"10.1016\/j.ress.2026.113057_b17","article-title":"Cognitive phantoms in large language models through the lens of latent variables","author":"Peereboom","year":"2025","journal-title":"Comput Hum Behav: Artif Humans"},{"key":"10.1016\/j.ress.2026.113057_b18","doi-asserted-by":"crossref","first-page":"2967","DOI":"10.1007\/s10115-024-02310-4","article-title":"Large language models: a survey of their development, capabilities, and applications","volume":"67","author":"Annepaka","year":"2025","journal-title":"Knowl Inf Syst"},{"key":"10.1016\/j.ress.2026.113057_b19","first-page":"1","article-title":"Security practices in AI development","author":"Spelda","year":"2025","journal-title":"AI Society"},{"key":"10.1016\/j.ress.2026.113057_b20","doi-asserted-by":"crossref","DOI":"10.1057\/s41599-024-03560-x","article-title":"AI governance in a complex and rapidly changing regulatory landscape: A global perspective","volume":"11","author":"Zaidan","year":"2024","journal-title":"Humanit Soc Sci Commun"},{"key":"10.1016\/j.ress.2026.113057_b21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/polsoc\/puaf001","article-title":"Governance of generative AI","volume":"44","author":"Taeihagh","year":"2025","journal-title":"Policy Soc"},{"key":"10.1016\/j.ress.2026.113057_b22","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1093\/polsoc\/puae020","article-title":"When code isn\u2019t law: rethinking regulation for artificial intelligence","volume":"44","author":"Judge","year":"2025","journal-title":"Policy Soc"},{"key":"10.1016\/j.ress.2026.113057_b23","series-title":"Anthropic, feds test whether AI will share sensitive nuke info","author":"Sabin","year":"2024"},{"key":"10.1016\/j.ress.2026.113057_b24","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1080\/17579961.2021.1898300","article-title":"From a \u2018race to AI\u2019to a \u2018race to AI regulation\u2019: Regulatory competition for artificial intelligence","volume":"13","author":"Smuha","year":"2021","journal-title":"Law Innov Technol"},{"key":"10.1016\/j.ress.2026.113057_b25","series-title":"Managing misuse risk for dual-use foundation models","author":"Institute","year":"2024"},{"key":"10.1016\/j.ress.2026.113057_b26","series-title":"Regulation (EU) 2024\/1689 of the European parliament and of the council. 2024","author":"Act, Artificial Intelligence","year":"2025"},{"key":"10.1016\/j.ress.2026.113057_b27","series-title":"Nougat: Neural optical understanding for academic documents","author":"Blecher","year":"2023"},{"key":"10.1016\/j.ress.2026.113057_b28","series-title":"Marker: PDF to markdown and JSON document conversion tool","author":"Datalab-to\/marker developers","year":"2025"},{"key":"10.1016\/j.ress.2026.113057_b29","series-title":"Docling technical report","author":"Auer","year":"2024"},{"key":"10.1016\/j.ress.2026.113057_b30","series-title":"Document parsing unveiled: Techniques, challenges, and prospects for structured information extraction","author":"Zhang","year":"2024"},{"key":"10.1016\/j.ress.2026.113057_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.egyai.2025.100555","article-title":"Automating Monte Carlo simulations in nuclear engineering with domain knowledge-embedded large language model agents","author":"Ndum","year":"2025","journal-title":"Energy AI"},{"key":"10.1016\/j.ress.2026.113057_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.rser.2024.114570","article-title":"Sentiment analysis of the United States public support of nuclear power on social media using large language models","volume":"200","author":"Kwon","year":"2024","journal-title":"Renew Sustain Energy Rev"},{"key":"10.1016\/j.ress.2026.113057_b33","doi-asserted-by":"crossref","unstructured":"Fan W, Ding Y, Ning L, Wang S, Li H, Yin D, Chua T-S, Li Q. A survey on rag meeting llms: Towards retrieval-augmented large language models. In: Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining. 2024, p. 6491\u2013501.","DOI":"10.1145\/3637528.3671470"},{"key":"10.1016\/j.ress.2026.113057_b34","series-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023"},{"key":"10.1016\/j.ress.2026.113057_b35","unstructured":"Athe P, Dinh N. Testing generative pre-trained transformer for knowledge abstraction and reasoning for nuclear reactor design and safety applications. Tech. rep., 2023, Probabilistic safety assessment and management (PSAM) topical, Virtual."},{"key":"10.1016\/j.ress.2026.113057_b36","series-title":"Nuclear security: A natural language processing generative approach","author":"Iob","year":"2024"},{"key":"10.1016\/j.ress.2026.113057_b37","doi-asserted-by":"crossref","first-page":"C07006","DOI":"10.1088\/1748-0221\/19\/07\/C07006","article-title":"Towards a RAG-based summarization for the electron ion collider","volume":"19","author":"Suresh","year":"2024","journal-title":"J Instrum"},{"key":"10.1016\/j.ress.2026.113057_b38","doi-asserted-by":"crossref","first-page":"C07001","DOI":"10.1088\/1748-0221\/19\/07\/C07001","article-title":"AI-assisted detector design for the EIC (AID (2) E)","volume":"19","author":"Diefenthaler","year":"2024","journal-title":"J Instrum"},{"key":"10.1016\/j.ress.2026.113057_b39","series-title":"DREAMS: Density functional theory based research engine for agentic materials simulation","author":"Wang","year":"2025"},{"key":"10.1016\/j.ress.2026.113057_b40","series-title":"KRAIL: A knowledge-driven framework for base human reliability analysis integrating IDHEAS and large language models","author":"Xiao","year":"2024"},{"key":"10.1016\/j.ress.2026.113057_b41","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6498\/ad1fdf","article-title":"Artificial intelligence model GPT4 narrowly fails simulated radiological protection exam","volume":"44","author":"Roemer","year":"2024","journal-title":"J Radiol Prot"},{"key":"10.1016\/j.ress.2026.113057_b42","first-page":"269","article-title":"Comparison of large language models\u2019 performance on 600 nuclear medicine technology board examination\u2013style questions","volume":"24","author":"Oumano","year":"2025","journal-title":"J Nucl Med Technol"},{"key":"10.1016\/j.ress.2026.113057_b43","doi-asserted-by":"crossref","DOI":"10.2196\/63887","article-title":"ChatGPT-4 performance on German continuing medical education\u2014Friend or foe (trick or treat)? Protocol for a randomized controlled trial","volume":"14","author":"Burisch","year":"2025","journal-title":"JMIR Res Protoc"},{"key":"10.1016\/j.ress.2026.113057_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.nuclcard.2024.102089","article-title":"Evaluating AI proficiency in nuclear cardiology: Large language models take on the board preparation exam","volume":"45","author":"Builoff","year":"2025","journal-title":"J Nucl Cardiol"},{"key":"10.1016\/j.ress.2026.113057_b45","doi-asserted-by":"crossref","DOI":"10.1007\/s10462-025-11477-3","article-title":"Deep learning based visually rich document content understanding: A survey","author":"Ding","year":"2026","journal-title":"Artif Intell Rev"},{"key":"10.1016\/j.ress.2026.113057_b46","doi-asserted-by":"crossref","unstructured":"Zhang J, Zhang Q, Wang B, Ouyang L, Wen Z, Li Y, Chow K-H, He C, Zhang W. OCR hinders rag: Evaluating the cascading impact of OCR on retrieval-augmented generation. In: Proceedings of the IEEE\/CVF international conference on computer vision. 2025, p. 17443\u201353.","DOI":"10.1109\/ICCV51701.2025.01620"},{"key":"10.1016\/j.ress.2026.113057_b47","doi-asserted-by":"crossref","unstructured":"Caffagni D, Cocchi F, Moratelli N, Sarto S, Cornia M, Baraldi L, Cucchiara R. Wiki-llava: Hierarchical retrieval-augmented generation for multimodal llms. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2024, p. 1818\u201326.","DOI":"10.1109\/CVPRW63382.2024.00188"},{"key":"10.1016\/j.ress.2026.113057_b48","series-title":"From local to global: A graph rag approach to query-focused summarization","author":"Edge","year":"2024"},{"key":"10.1016\/j.ress.2026.113057_b49","doi-asserted-by":"crossref","unstructured":"Kalra R, Wu Z, Gulley A, Hilliard A, Guan X, Koshiyama A, Treleaven PC. HyPA-RAG: A hybrid parameter adaptive retrieval-augmented generation system for AI legal and policy applications. In: Proceedings of the 1st workshop on customizable NLP: progress and challenges in customizing NLP for a domain, application, group, or individual (customnlp4u). 2024, p. 237\u201356.","DOI":"10.18653\/v1\/2024.customnlp4u-1.18"},{"key":"10.1016\/j.ress.2026.113057_b50","series-title":"Proceedings of the 66th annual international nuclear materials management (INMM) meeting","article-title":"RADIANT-LLM: Retrieval-augmented domain intelligent LLM framework for safe, secure, and safeguarded design of advanced nuclear reactor technologies","author":"Ndum","year":"2025"},{"key":"10.1016\/j.ress.2026.113057_b51","series-title":"GitHub - langchain-AI\/langchain: Build context-aware reasoning applications","author":"Chase","year":"2023"},{"key":"10.1016\/j.ress.2026.113057_b52","series-title":"Automating Customer Service using LangChain: Building custom open-source GPT Chatbot for organizations","author":"Pandya","year":"2023"},{"key":"10.1016\/j.ress.2026.113057_b53","first-page":"129","article-title":"Generative AI service implementation using LLM application architecture: based on RAG model and LangChain framework","volume":"29","author":"Jeong","year":"2023","journal-title":"J Intell Inf Syst"},{"key":"10.1016\/j.ress.2026.113057_b54","doi-asserted-by":"crossref","unstructured":"Singh A, Ehtesham A, Mahmud S, Kim J-H. Revolutionizing mental health care through langchain: A journey with a large language model. In: 2024 IEEE 14th annual computing and communication workshop and conference. 2024, p. 73\u20138.","DOI":"10.1109\/CCWC60891.2024.10427865"},{"key":"10.1016\/j.ress.2026.113057_b55","series-title":"Nougat: Neural optical understanding for academic documents","author":"Blecher","year":"2023"},{"key":"10.1016\/j.ress.2026.113057_b56","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"10.1016\/j.ress.2026.113057_b57","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J. Bleu: A method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics. 2002, p. 311\u20138.","DOI":"10.3115\/1073083.1073135"},{"key":"10.1016\/j.ress.2026.113057_b58","unstructured":"Chin-Yew L. Rouge: A package for automatic evaluation of summaries. In: Proceedings of the workshop on text summarization branches out, 2004. 2004."},{"key":"10.1016\/j.ress.2026.113057_b59","series-title":"Squad: 100,000+ questions for machine comprehension of text","author":"Rajpurkar","year":"2016"},{"key":"10.1016\/j.ress.2026.113057_b60","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2026.104651","article-title":"GAI-HIQ: Developing a health information quality assessment indicator system for generative artificial intelligence","volume":"63","author":"Yi","year":"2026","journal-title":"Inf Process Manage"},{"issue":"2","key":"10.1016\/j.ress.2026.113057_b61","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1037\/0033-2909.86.2.420","article-title":"Intraclass correlations: Uses in assessing rater reliability","volume":"86","author":"Shrout","year":"1979","journal-title":"Psychol Bull"},{"key":"10.1016\/j.ress.2026.113057_b62","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","author":"Holm","year":"1979","journal-title":"Scand J Stat"},{"key":"10.1016\/j.ress.2026.113057_b63","series-title":"Calculus","first-page":"xvi + 360","author":"March","year":"1917"},{"key":"10.1016\/j.ress.2026.113057_b64","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2024.110382","article-title":"Empirical study on fine-tuning pre-trained large language models for fault diagnosis of complex systems","volume":"252","author":"Zheng","year":"2024","journal-title":"Reliab Eng Syst Saf"},{"key":"10.1016\/j.ress.2026.113057_b65","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2025.111585","article-title":"KRAIL: A knowledge-driven framework for human reliability analysis integrating IDHEAS-DATA and large language models","volume":"265","author":"Xiao","year":"2026","journal-title":"Reliab Eng Syst Saf","ISSN":"https:\/\/id.crossref.org\/issn\/0951-8320","issn-type":"print"},{"key":"10.1016\/j.ress.2026.113057_b66","doi-asserted-by":"crossref","DOI":"10.1016\/j.ress.2025.111973","article-title":"Lightweight multimodal LLM-empowered dual-agent collaboration for reliable defect detection and maintenance recommendation in tunnel infrastructure","volume":"268","author":"Yu","year":"2026","journal-title":"Reliab Eng Syst Saf"}],"container-title":["Reliability Engineering & System Safety"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0951832026008665?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0951832026008665?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T12:00:34Z","timestamp":1785844834000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0951832026008665"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":66,"alternative-id":["S0951832026008665"],"URL":"https:\/\/doi.org\/10.1016\/j.ress.2026.113057","relation":{},"ISSN":["0951-8320"],"issn-type":[{"value":"0951-8320","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A retrieval-augmented, domain-intelligent agentic framework for reliable decision support in safety-critical nuclear engineering","name":"articletitle","label":"Article Title"},{"value":"Reliability Engineering & System Safety","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ress.2026.113057","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113057"}}