{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:59:07Z","timestamp":1781225947832,"version":"3.54.1"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/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":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.knosys.2026.115989","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:23:04Z","timestamp":1776100984000},"page":"115989","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Automating data-driven modeling and analysis for engineering applications using large language model agents"],"prefix":"10.1016","volume":"343","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1337-2527","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4976-6896","authenticated-orcid":false,"given":"Zaid","family":"Abulawi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhiram","family":"Garimidi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1259-1631","authenticated-orcid":false,"given":"Doyeong","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.115989_b1","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1016\/j.applthermaleng.2018.08.041","article-title":"Data-driven modeling for boiling heat transfer: using deep neural networks and high-fidelity simulation results","volume":"144","author":"Liu","year":"2018","journal-title":"Appl. Therm. Eng."},{"key":"10.1016\/j.knosys.2026.115989_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.nucengdes.2022.111716","article-title":"Data-driven modeling of coarse mesh turbulence for reactor transient analysis using convolutional recurrent neural networks","volume":"390","author":"Liu","year":"2022","journal-title":"Nucl. Eng. Des."},{"issue":"2","key":"10.1016\/j.knosys.2026.115989_b3","doi-asserted-by":"crossref","DOI":"10.1063\/5.0253234","article-title":"High-to-low flow dynamics learning with deep convolutional encoder\u2013decoder networks for randomly packed pebble-bed geometry","volume":"37","author":"Lanade","year":"2025","journal-title":"Phys. Fluids"},{"key":"10.1016\/j.knosys.2026.115989_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.anucene.2020.107916","article-title":"A hybrid porous model for full reactor core scale CFD investigation of a prismatic HTGR","volume":"151","author":"Wang","year":"2021","journal-title":"Ann. Nucl. Energy"},{"key":"10.1016\/j.knosys.2026.115989_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.nucengdes.2022.112059","article-title":"SAM-ML: Integrating data-driven closure with nuclear system code SAM for improved modeling capability","volume":"400","author":"Liu","year":"2022","journal-title":"Nucl. Eng. Des."},{"key":"10.1016\/j.knosys.2026.115989_b6","first-page":"1","article-title":"Development of whole system digital twins for advanced reactors: Leveraging graph neural networks and SAM simulations","author":"Liu","year":"2024","journal-title":"Nucl. Technol."},{"key":"10.1016\/j.knosys.2026.115989_b7","article-title":"Benchmark on artificial intelligence and machine learning for scientific computing in nuclear engineering. Phase 1: Critical heat flux exercise specifications","volume":"1","author":"le Corre","year":"2023","journal-title":"NEA\/WKP"},{"key":"10.1016\/j.knosys.2026.115989_b8","article-title":"A comprehensive survey on integrating large language models with knowledge-based methods","author":"Yang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115989_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112155","article-title":"Enhancing text-based knowledge graph completion with zero-shot large language models: A focus on semantic enhancement","volume":"300","author":"Yang","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115989_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113060","article-title":"Large language models can better understand knowledge graphs than we thought","author":"Dai","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115989_b11","article-title":"Prompting large language models with knowledge graphs for question answering involving long-tail facts","author":"Huang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115989_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113396","article-title":"Harnessing code domain insights: Enhancing programming knowledge tracing with large language models","volume":"317","author":"Sun","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115989_b13","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113431","article-title":"Knowledge-embedded large language models for emergency triage","volume":"318","author":"Shen","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115989_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.111395","article-title":"Knowledge-based dynamic prompt learning for multi-label disease diagnosis","volume":"286","author":"Xie","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115989_b15","article-title":"Large language model based system with causal inference and chain-of-thoughts reasoning for traffic scene risk assessment","author":"Zhong","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115989_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112758","article-title":"Soft prompt tuning for augmenting dense retrieval with large language models","volume":"309","author":"Peng","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115989_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113151","article-title":"Automatically resolving conflicts between expert systems: An experimental approach using large language models and fuzzy cognitive maps from participatory modeling studies","volume":"313","author":"Schuerkamp","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115989_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113569","article-title":"Fairness and social bias quantification in large language models for sentiment analysis","author":"Radaideh","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"10.1016\/j.knosys.2026.115989_b19","series-title":"AI agents vs. agentic AI: a conceptual taxonomy, applications and challenge","author":"Sapkota","year":"2025"},{"key":"10.1016\/j.knosys.2026.115989_b20","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.knosys.2026.115989_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.eml.2024.102131","article-title":"MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge","volume":"67","author":"Ni","year":"2024","journal-title":"Extrem. Mech. Lett."},{"key":"10.1016\/j.knosys.2026.115989_b22","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"13936","article-title":"BLADE: Benchmarking language model agents for data-driven science","author":"Gu","year":"2024"},{"key":"10.1016\/j.knosys.2026.115989_b23","unstructured":"S. Yao, J. Zhao, D. Yu, N. Du, I. Shafran, K.R. Narasimhan, Y. Cao, ReAct: Synergizing Reasoning and Acting in Language Models, in: The Eleventh International Conference on Learning Representations, 2023."},{"key":"10.1016\/j.knosys.2026.115989_b24","unstructured":"S. Hong, M. Zhuge, J. Chen, X. Zheng, Y. Cheng, J. Wang, C. Zhang, Z. Wang, S.K.S. Yau, Z. Lin, L. Zhou, C. Ran, L. Xiao, C. Wu, J. Schmidhuber, MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework, in: The Twelfth International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.knosys.2026.115989_b25","doi-asserted-by":"crossref","unstructured":"O. Topsakal, T.C. Akinci, Creating large language model applications utilizing langchain: A primer on developing llm apps fast, in: International Conference on Applied Engineering and Natural Sciences, Vol. 1, 2023, pp. 1050\u20131056.","DOI":"10.59287\/icaens.1127"},{"key":"10.1016\/j.knosys.2026.115989_b26","series-title":"Autogen: Enabling next-gen llm applications via multi-agent conversation","author":"Wu","year":"2023"},{"issue":"15\u201317","key":"10.1016\/j.knosys.2026.115989_b27","doi-asserted-by":"crossref","first-page":"1909","DOI":"10.1016\/j.nucengdes.2007.02.014","article-title":"The 2006 CHF look-up table","volume":"237","author":"Groeneveld","year":"2007","journal-title":"Nucl. Eng. Des."},{"key":"10.1016\/j.knosys.2026.115989_b28","series-title":"OpenAI agents SDK","author":"OpenAI","year":"2024"},{"key":"10.1016\/j.knosys.2026.115989_b29","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"5","key":"10.1016\/j.knosys.2026.115989_b30","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Netw."},{"key":"10.1016\/j.knosys.2026.115989_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.icheatmasstransfer.2024.107844","article-title":"Assessment of the state-of-the-art AI methods for critical heat flux prediction","volume":"158","author":"Zhou","year":"2024","journal-title":"Int. Commun. Heat Mass Transfer"},{"key":"10.1016\/j.knosys.2026.115989_b32","article-title":"Re-examining the input-parameters and AI strategies for critical heat flux prediction","volume":"318","author":"Wang","year":"2025","journal-title":"Energy"},{"key":"10.1016\/j.knosys.2026.115989_b33","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1016\/j.ijheatmasstransfer.2019.04.075","article-title":"Uncertainty quantification of two-phase flow and boiling heat transfer simulations through a data-driven modular Bayesian approach","volume":"138","author":"Liu","year":"2019","journal-title":"Int. J. Heat Mass Transfer"},{"key":"10.1016\/j.knosys.2026.115989_b34","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."},{"issue":"12","key":"10.1016\/j.knosys.2026.115989_b35","doi-asserted-by":"crossref","first-page":"2002","DOI":"10.1080\/00295450.2022.2162792","article-title":"Uncertainty quantification for multiphase computational fluid dynamics closure relations with a physics-informed bayesian approach","volume":"209","author":"Liu","year":"2023","journal-title":"Nucl. Technol."},{"key":"10.1016\/j.knosys.2026.115989_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.nucengdes.2020.110677","article-title":"Uncertainty analysis of PIV measurements in bubbly flows considering sampling and bubble effects with ray optics modeling","volume":"364","author":"Liu","year":"2020","journal-title":"Nucl. Eng. Des."},{"key":"10.1016\/j.knosys.2026.115989_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.anucene.2023.110010","article-title":"Benchmarking FFTF LOFWOS test# 13 using SAM code: Baseline model development and uncertainty quantification","volume":"192","author":"Liu","year":"2023","journal-title":"Ann. Nucl. Energy"},{"key":"10.1016\/j.knosys.2026.115989_b38","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume":"30","author":"Lakshminarayanan","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.knosys.2026.115989_b39","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.knosys.2026.115989_b40","series-title":"Verification and Validation","article-title":"Uncertainty quantification of deep neural network-based turbulence model for reactor transient analysis","volume":"84782","author":"Liu","year":"2021"},{"key":"10.1016\/j.knosys.2026.115989_b41","doi-asserted-by":"crossref","DOI":"10.1016\/j.anucene.2026.112139","article-title":"Bayesian-optimized, feature-augmented deep ensemble for physics-guided critical heat-flux prediction with uncertainty quantification","volume":"230","author":"Abulawi","year":"2026","journal-title":"Ann. Nucl. Energy"},{"key":"10.1016\/j.knosys.2026.115989_b42","doi-asserted-by":"crossref","unstructured":"O. Gokdemir, et al., HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights, in: Proceedings of the Platform for Advanced Scientific Computing Conference, 2025, pp. 1\u201313.","DOI":"10.1145\/3732775.3733586"},{"key":"10.1016\/j.knosys.2026.115989_b43","series-title":"Bayesian hyperparameter optimization with BoTorch, GPyTorch and Ax","author":"Chang","year":"2019"},{"key":"10.1016\/j.knosys.2026.115989_b44","first-page":"1","article-title":"CNN-transformer bridge mode for detecting arcing horn defects in railway sectional insulator","volume":"73","author":"He","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"1","key":"10.1016\/j.knosys.2026.115989_b45","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1109\/TMECH.2025.3587940","article-title":"Multiscale cross-attention CNN-transformer two-branch fusion network for detecting railway U-shaped bolts & nuts defects","volume":"31","author":"He","year":"2026","journal-title":"IEEE\/ASME Trans. Mechatronics"},{"issue":"6","key":"10.1016\/j.knosys.2026.115989_b46","doi-asserted-by":"crossref","first-page":"8894","DOI":"10.1109\/TITS.2025.3540846","article-title":"Multi-scale CNN-transformer hybrid network for rail fastener defect detection","volume":"26","author":"He","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.knosys.2026.115989_b47","first-page":"1","article-title":"C2T-HR3D: Cross-fusion of CNN and transformer for high-speed railway dropper defect detection","volume":"74","author":"He","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.knosys.2026.115989_b48","doi-asserted-by":"crossref","DOI":"10.1016\/j.pnucene.2025.106172","article-title":"Large language model-assisted digital twin for remote monitoring and control of advanced reactors","volume":"192","author":"Ndum","year":"2026","journal-title":"Prog. Nucl. Energy"}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512600715X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095070512600715X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:13:36Z","timestamp":1781223216000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095070512600715X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":48,"alternative-id":["S095070512600715X"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115989","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Automating data-driven modeling and analysis for engineering applications using large language model agents","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.115989","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 B.V.","name":"copyright","label":"Copyright"}],"article-number":"115989"}}