{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T08:04:11Z","timestamp":1784534651415,"version":"3.55.0"},"reference-count":51,"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":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.eswa.2026.133537","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T12:48:02Z","timestamp":1783601282000},"page":"133537","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["Large language model guided multi-objective reward optimization for maintenance decision-making"],"prefix":"10.1016","volume":"332","author":[{"given":"Qixuan","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laifa","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanyuan","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0878-9344","authenticated-orcid":false,"given":"Zhixuan","family":"Lian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133537_b0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.ymssp.2019.106570","article-title":"An optimal maintenance strategy for multi-state deterioration systems based on a semi-Markov decision process coupled with simulation technique","volume":"139","author":"Jin","year":"2020","journal-title":"Mechanical Systems and Signal Processing"},{"key":"10.1016\/j.eswa.2026.133537_b0010","article-title":"Interactive Process Drift Detection (IPDD) for condition-based maintenance using process mining","volume":"66","author":"Sato","year":"2025","journal-title":"Advanced Engineering Informatics"},{"key":"10.1016\/j.eswa.2026.133537_b0015","article-title":"Machine-Learning- and Internet-of-Things-Driven Techniques for monitoring Tool Wear in Machining Process: A Comprehensive Review","volume":"13","author":"Rakkiyannan","year":"2024","journal-title":"Journal of Sensor and Actuator Networks"},{"issue":"4","key":"10.1016\/j.eswa.2026.133537_b0020","doi-asserted-by":"crossref","first-page":"6234","DOI":"10.1109\/TII.2022.3201977","article-title":"Incremental learning for remaining useful life prediction via temporal cascade broad learning system with newly acquired data","volume":"19","author":"Cao","year":"2022","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"10.1016\/j.eswa.2026.133537_b0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.ymssp.2022.108873","article-title":"Application of deep reinforcement learning for extremely rare failure prediction in aircraft maintenance","volume":"171","author":"Dangut","year":"2022","journal-title":"Mechanical Systems and Signal Processing"},{"key":"10.1016\/j.eswa.2026.133537_b0030","first-page":"1","article-title":"Deep multi-objective reinforcement learning for utility-based infrastructural maintenance optimization","author":"van Remmerden","year":"2025","journal-title":"Neural Computing and Applications"},{"issue":"10","key":"10.1016\/j.eswa.2026.133537_b0035","doi-asserted-by":"crossref","DOI":"10.1007\/s10994-024-06559-2","article-title":"POMDP inference and robust solution via deep reinforcement learning: An application to railway optimal maintenance","volume":"113","author":"Arcieri","year":"2024","journal-title":"Machine Learning"},{"key":"10.1016\/j.eswa.2026.133537_b0040","first-page":"1","article-title":"A deep reinforcement learning assisted simulated annealing algorithm for a maintenance planning problem","author":"Kosanoglu","year":"2022","journal-title":"Ann. Oper. Res."},{"key":"10.1016\/j.eswa.2026.133537_b0045","first-page":"1","article-title":"Predictive maintenance for edge-based sensor networks: A deep reinforcement learning approach[C]\/\/2020 IEEE 6th World Forum on internet of things (WF-IoT)","author":"Ong","year":"2020","journal-title":"IEEE"},{"issue":"24","key":"10.1016\/j.eswa.2026.133537_b0050","doi-asserted-by":"crossref","first-page":"4020","DOI":"10.3390\/math12244020","article-title":"A Self-Rewarding Mechanism in Deep Reinforcement Learning for trading Strategy Optimization","volume":"12","author":"Huang","year":"2024","journal-title":"Mathematics"},{"issue":"14","key":"10.1016\/j.eswa.2026.133537_b0055","doi-asserted-by":"crossref","first-page":"5873","DOI":"10.3390\/su16145873","article-title":"Advancing sustainable manufacturing: Reinforcement learning with adaptive reward machine using an ontology-based approach","volume":"16","author":"Golpayegani","year":"2024","journal-title":"Sustainability"},{"issue":"1","key":"10.1016\/j.eswa.2026.133537_b0060","doi-asserted-by":"crossref","first-page":"13755","DOI":"10.1038\/s41598-025-98483-1","article-title":"Industrial applications of large language models","volume":"15","author":"Raza","year":"2025","journal-title":"Scientific Reports"},{"key":"10.1016\/j.eswa.2026.133537_b0065","article-title":"Operator-in-the-Loop Multi-Objective Scheduling of Multi-Energy Microgrids via LLM-Guided Reinforcement Learning","author":"Liu","year":"2025","journal-title":"IEEE Transactions on Industry Applications"},{"issue":"4","key":"10.1016\/j.eswa.2026.133537_b0070","doi-asserted-by":"crossref","DOI":"10.1049\/cim2.70007","article-title":"A multimodal expert system for the intelligent monitoring and maintenance of transformers enhanced by multimodal language large model fine\u2010tuning and digital twins","volume":"6","author":"Zhang","year":"2024","journal-title":"IET Collaborative Intelligent Manufacturing"},{"key":"10.1016\/j.eswa.2026.133537_b0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2021.101360","article-title":"Deep reinforcement learning-based safe interaction for industrial human-robot collaboration using intrinsic reward function","volume":"49","author":"Liu","year":"2021","journal-title":"Advanced Engineering Informatics"},{"key":"10.1016\/j.eswa.2026.133537_b0080","doi-asserted-by":"crossref","first-page":"64735","DOI":"10.52202\/079017-2066","article-title":"Rest-mcts*: Llm self-training via process reward guided tree search","volume":"37","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133537_b0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2020.113701","article-title":"Deep reinforcement learning based preventive maintenance policy for serial production lines","volume":"160","author":"Huang","year":"2020","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133537_b0090","article-title":"A reinforcement learning agent for maintenance of deteriorating systems with increasingly imperfect repairs","volume":"252","author":"Marug\u00e1n","year":"2024","journal-title":"Reliability Engineering & System Safety"},{"key":"10.1016\/j.eswa.2026.133537_b0095","first-page":"571","article-title":"Deep reinforcement learning for optimal life-cycle management of deteriorating regional bridges using double-deep Q-networks","author":"Dong","year":"2022","journal-title":"Smart Structures and Systems"},{"key":"10.1016\/j.eswa.2026.133537_b0100","unstructured":"Kumar P, Misra R. ARDDQN: Attention recurrent double deep Q-network for UAV coverage path planning and data harvesting. arXiv preprint arXiv:2405.11013, 2024."},{"issue":"12","key":"10.1016\/j.eswa.2026.133537_b0105","doi-asserted-by":"crossref","first-page":"1195","DOI":"10.3390\/machines10121195","article-title":"Hierarchical reinforcement learning for multi-objective real-time flexible scheduling in a smart shop floor","volume":"10","author":"Chang","year":"2022","journal-title":"Machines"},{"key":"10.1016\/j.eswa.2026.133537_b0110","series-title":"11th International Conference on Wireless Networks and Mobile Communications (WINCOM)","first-page":"1","article-title":"Continuous transfer learning for UAV communication-aware trajectory design[C]\/\/2024","author":"Sun","year":"2024"},{"key":"10.1016\/j.eswa.2026.133537_b0115","article-title":"Hybrid reward architecture for reinforcement learning","volume":"30","author":"Van Seijen","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"10.1016\/j.eswa.2026.133537_b0120","doi-asserted-by":"crossref","first-page":"e23","DOI":"10.1017\/S0269888918000292","article-title":"Reward shaping for knowledge-based multi-objective multi-agent reinforcement learning","volume":"33","author":"Mannion","year":"2018","journal-title":"The Knowledge Engineering Review"},{"key":"10.1016\/j.eswa.2026.133537_b0125","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2021.103500","article-title":"A survey of inverse reinforcement learning: Challenges, methods and progress","volume":"297","author":"Arora","year":"2021","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.133537_b0130","unstructured":"Cherukuri K, Lala A. Learning Pareto-Optimal Rewards from Noisy Preferences: A Framework for Multi-Objective Inverse Reinforcement Learning. arXiv preprint arXiv:2505.11864, 2025."},{"key":"10.1016\/j.eswa.2026.133537_b0135","doi-asserted-by":"crossref","DOI":"10.1016\/j.ymssp.2024.112127","article-title":"LLM-based framework for bearing fault diagnosis","volume":"224","author":"Tao","year":"2025","journal-title":"Mechanical Systems and Signal Processing"},{"key":"10.1016\/j.eswa.2026.133537_b0140","unstructured":"Tao L, Huang Q, Wu X, et al. LLM-R: A Framework for Domain-Adaptive Maintenance Scheme Generation Combining Hierarchical Agents and RAG. arXiv preprint arXiv:2411.04476, 2024."},{"key":"10.1016\/j.eswa.2026.133537_b0145","doi-asserted-by":"crossref","unstructured":"Duranti D, Giorgini P, Mazzullo A, et al. LLM-driven knowledge extraction in temporal and description logics[C]\/\/International conference on knowledge engineering and knowledge management. Cham: Springer Nature Switzerland, 2024: 190-208.","DOI":"10.1007\/978-3-031-77792-9_12"},{"issue":"16","key":"10.1016\/j.eswa.2026.133537_b0150","doi-asserted-by":"crossref","first-page":"32296","DOI":"10.1109\/JIOT.2024.3503274","article-title":"Brain-like cognition-driven model factory for IIoT fault diagnosis by combining LLMs with small models","volume":"12","author":"Liu","year":"2024","journal-title":"IEEE Internet of Things Journal"},{"key":"10.1016\/j.eswa.2026.133537_b0155","unstructured":"Zeng Y, Mu Y, Shao L. Learning reward for robot skills using large language models via self-alignment[C]\/\/Proceedings of the 41st International Conference on Machine Learning. PMLR, 2024, 235: 58366\u201358386."},{"key":"10.1016\/j.eswa.2026.133537_b0160","unstructured":"Du Y, Watkins O, Wang Z, et al. Guiding pretraining in reinforcement learning with large language models[C]\/\/International Conference on Machine Learning. PMLR, 2023: 8657-8677."},{"key":"10.1016\/j.eswa.2026.133537_b0165","first-page":"26516","article-title":"Eureka: Human-level reward design via coding large language models[C]\/\/International conference on learning","author":"Ma","year":"2024","journal-title":"Representations"},{"issue":"2","key":"10.1016\/j.eswa.2026.133537_b0170","doi-asserted-by":"crossref","first-page":"2923","DOI":"10.59400\/cai2923","article-title":"Multifidelity Bayesian optimization for hyperparameter tuning of deep reinforcement learning algorithms","volume":"3","author":"Garrido-Merch\u00e1n","year":"2025","journal-title":"Computing and Artificial Intelligence"},{"key":"10.1016\/j.eswa.2026.133537_b0175","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.106247","article-title":"Fast hyperparameter tuning using Bayesian optimization with directional derivatives","volume":"205","author":"Joy","year":"2020","journal-title":"Knowledge-Based Systems"},{"key":"10.1016\/j.eswa.2026.133537_b0180","article-title":"Neural architecture search with bayesian optimisation and optimal transport","volume":"31","author":"Kandasamy","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"10.1016\/j.eswa.2026.133537_b0185","doi-asserted-by":"crossref","first-page":"93118","DOI":"10.52202\/079017-2956","article-title":"Batched energy-entropy acquisition for Bayesian optimization","volume":"37","author":"Teufel","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.133537_b0190","article-title":"Multi-fidelity Bayesian optimization with across-task transferable max-value entropy search","author":"Zhang","year":"2025","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10.1016\/j.eswa.2026.133537_b0195","unstructured":"Koo R, Yang I, Raheja V, et al. Learning explainable dense reward shapes via bayesian optimization. arXiv preprint arXiv:2504.16272, 2025."},{"key":"10.1016\/j.eswa.2026.133537_b0200","doi-asserted-by":"crossref","unstructured":"A. Saxena, K. Goebel, D. Simon, and N. Eklund, \u201cDamage Propagation Modeling for Aircraft Engine Run-to-Failure Simulation\u201d, in the Proceedings of the Ist International Conference on Prognostics and Health Management (PHM08), Denver CO, Oct 2008.","DOI":"10.1109\/PHM.2008.4711414"},{"issue":"1","key":"10.1016\/j.eswa.2026.133537_b0205","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1109\/TR.2018.2882682","article-title":"A Hybrid Prognostics Approach for estimating remaining Useful Life of Rolling Element Bearings","volume":"69","author":"Wang","year":"2020","journal-title":"IEEE Transactions on Reliability"},{"key":"10.1016\/j.eswa.2026.133537_b0210","unstructured":"Dubey A, Jauhri A, Pandey A, et al. The Llama 3 herd of models. arXiv preprint arXiv:2407.21783, 2024."},{"key":"10.1016\/j.eswa.2026.133537_b0215","unstructured":"Hurst A, Lerer A, Goucher A P, et al. Gpt-4o system card. arXiv preprint arXiv:2410.21276, 2024."},{"issue":"13","key":"10.1016\/j.eswa.2026.133537_b0220","doi-asserted-by":"crossref","first-page":"2657","DOI":"10.3390\/electronics13132657","article-title":"Enhancing software code vulnerability detection using gpt-4o and claude-3.5 sonnet: A study on prompt engineering techniques","volume":"13","author":"Bae","year":"2024","journal-title":"Electronics"},{"key":"10.1016\/j.eswa.2026.133537_b0225","unstructured":"Yang A, Zhang B, Hui B, et al. Qwen2. 5-math technical report: Toward mathematical expert model via self-improvement. arXiv preprint arXiv:2409.12122, 2024."},{"key":"10.1016\/j.eswa.2026.133537_b0230","unstructured":"Guo D, Yang D, Zhang H, et al. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning\u2018. arXiv preprint arXiv:2501.12948, 2025."},{"key":"10.1016\/j.eswa.2026.133537_b0235","series-title":"in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"139","article-title":"Learning to prompt for continual learning","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2026.133537_b0240","first-page":"631","article-title":"DualPrompt: Complementary prompting for rehearsal-free continual learning, in","author":"Wang","year":"2022","journal-title":"European Conference on Computer Vision, Springer"},{"key":"10.1016\/j.eswa.2026.133537_b0245","series-title":"in: Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"11463","article-title":"Introducing language guidance in prompt-based continual learning","author":"Khan","year":"2023"},{"key":"10.1016\/j.eswa.2026.133537_b0250","unstructured":"Hsu C W, Chang C C, Lin C J. A practical guide to support vector classification[R]. Taipei: National Taiwan University, 2003."},{"key":"10.1016\/j.eswa.2026.133537_b0255","first-page":"1942","article-title":"Particle swarm optimization[C]\/\/Proceedings of ICNN'95-international conference on neural networks","volume":"4","author":"Kennedy","year":"1995","journal-title":"ieee"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426024462?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426024462?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T07:23:01Z","timestamp":1784532181000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426024462"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":51,"alternative-id":["S0957417426024462"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133537","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Large language model guided multi-objective reward optimization for maintenance decision-making","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133537","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133537"}}