{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T00:11:12Z","timestamp":1778717472461,"version":"3.51.4"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,4,21]],"date-time":"2027-04-21T00:00:00Z","timestamp":1808265600000},"content-version":"am","delay-in-days":263,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006377","name":"Purdue University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006377","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computers & Chemical Engineering"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.compchemeng.2026.109672","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T14:58:06Z","timestamp":1776697086000},"page":"109672","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["TalkToAgent: A multi-agent LLM Framework for natural language explanation of reinforcement learning policies"],"prefix":"10.1016","volume":"211","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0347-9297","authenticated-orcid":false,"given":"Haechang","family":"Kim","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6387-865X","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2859-7542","authenticated-orcid":false,"given":"Can","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5395-0067","authenticated-orcid":false,"given":"Jong Min","family":"Lee","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.compchemeng.2026.109672_b1","series-title":"2024 IEEE 10th International Conference on Network Softwarization","first-page":"204","article-title":"Leveraging LLMs to explain DRL decisions for transparent 6G network slicing","author":"Ameur","year":"2024"},{"key":"10.1016\/j.compchemeng.2026.109672_b2","doi-asserted-by":"crossref","unstructured":"Amitai, Y., Septon, Y., Amir, O., 2024. Explaining reinforcement learning agents through counterfactual action outcomes. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 38, pp. 10003\u201310011.","DOI":"10.1609\/aaai.v38i9.28863"},{"key":"10.1016\/j.compchemeng.2026.109672_b3","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2024.3431437","article-title":"Explainable artificial intelligence for autonomous driving: A comprehensive overview and field guide for future research directions","author":"Atakishiyev","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.compchemeng.2026.109672_b4","series-title":"Exploratory not explanatory: Counterfactual analysis of saliency maps for deep reinforcement learning","author":"Atrey","year":"2019"},{"key":"10.1016\/j.compchemeng.2026.109672_b5","series-title":"PC-Gym: Benchmark environments for process control problems","author":"Bloor","year":"2024"},{"key":"10.1016\/j.compchemeng.2026.109672_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2020.106844","article-title":"Stochastic data-driven model predictive control using gaussian processes","volume":"139","author":"Bradford","year":"2020","journal-title":"Comput. Chem. Eng."},{"issue":"4","key":"10.1016\/j.compchemeng.2026.109672_b7","first-page":"573","article-title":"Diagnosing infeasible optimization problems using large language models","volume":"62","author":"Chen","year":"2024","journal-title":"INFOR Inf. Syst. Oper. Res."},{"key":"10.1016\/j.compchemeng.2026.109672_b8","doi-asserted-by":"crossref","DOI":"10.1287\/ijds.2025.0074.cd","article-title":"OptiChat: Bridging optimization models and practitioners with large language models","author":"Chen","year":"2025","journal-title":"INFORMS J. Data Sci."},{"key":"10.1016\/j.compchemeng.2026.109672_b9","series-title":"International Conference on Machine Learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"},{"issue":"9","key":"10.1016\/j.compchemeng.2026.109672_b10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3648472","article-title":"Redefining counterfactual explanations for reinforcement learning: Overview, challenges and opportunities","volume":"56","author":"Gajcin","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.compchemeng.2026.109672_b11","series-title":"International Conference on Machine Learning","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.compchemeng.2026.109672_b12","series-title":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"3929","article-title":"Establishing appropriate trust via critical states","author":"Huang","year":"2018"},{"issue":"3","key":"10.1016\/j.compchemeng.2026.109672_b13","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1109\/87.845876","article-title":"The quadruple-tank process: A multivariable laboratory process with an adjustable zero","volume":"8","author":"Johansson","year":"2002","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"10.1016\/j.compchemeng.2026.109672_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2025.109152","article-title":"FaultExplainer: Leveraging large language models for interpretable fault detection and diagnosis","volume":"199","author":"Khan","year":"2025","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109672_b15","series-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015"},{"key":"10.1016\/j.compchemeng.2026.109672_b16","series-title":"Contrastive explanations for reinforcement learning via embedded self predictions","author":"Lin","year":"2020"},{"key":"10.1016\/j.compchemeng.2026.109672_b17","series-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","first-page":"414","article-title":"Toward interpretable deep reinforcement learning with linear model u-trees","author":"Liu","year":"2018"},{"key":"10.1016\/j.compchemeng.2026.109672_b18","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compchemeng.2026.109672_b19","doi-asserted-by":"crossref","unstructured":"Madumal, P., Miller, T., Sonenberg, L., Vetere, F., 2020. Explainable reinforcement learning through a causal lens. In: Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 34, pp. 2493\u20132500.","DOI":"10.1609\/aaai.v34i03.5631"},{"issue":"8","key":"10.1016\/j.compchemeng.2026.109672_b20","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1002\/tee.70005","article-title":"Reward design using large language models for natural language explanation of reinforcement learning agent actions","volume":"20","author":"Masadome","year":"2025","journal-title":"IEEJ Trans. Electr. Electron. Eng."},{"issue":"7","key":"10.1016\/j.compchemeng.2026.109672_b21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3616864","article-title":"Explainable reinforcement learning: A survey and comparative review","volume":"56","author":"Milani","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.compchemeng.2026.109672_b22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.artint.2018.07.007","article-title":"Explanation in artificial intelligence: Insights from the social sciences","volume":"267","author":"Miller","year":"2019","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.compchemeng.2026.109672_b23","unstructured":"Mishra, S., Jadhav, V.S., Karande, S., Runkana, V., 2024. Design and optimization of heat exchangers using large language models. In: Fourth Workshop on Knowledge-Infused Learning."},{"key":"10.1016\/j.compchemeng.2026.109672_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2025.109383","article-title":"Real-World implementation of offline reinforcement learning for process control in industrial dividing wall column","volume":"204","author":"Park","year":"2026","journal-title":"Comput. Chem. Eng."},{"issue":"1","key":"10.1016\/j.compchemeng.2026.109672_b25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s12555-024-0990-1","article-title":"Reinforcement learning for process control: Review and benchmark problems","volume":"23","author":"Park","year":"2025","journal-title":"Int. J. Control. Autom. Syst."},{"key":"10.1016\/j.compchemeng.2026.109672_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2023.108232","article-title":"A practical reinforcement learning implementation approach for continuous process control","volume":"174","author":"Patel","year":"2023","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109672_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.rser.2020.110618","article-title":"Applications of reinforcement learning in energy systems","volume":"137","author":"Perera","year":"2021","journal-title":"Renew. Sustain. Energy Rev."},{"key":"10.1016\/j.compchemeng.2026.109672_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.jclepro.2024.142824","article-title":"Large language models for life cycle assessments: Opportunities, challenges, and risks","volume":"466","author":"Preuss","year":"2024","journal-title":"J. Clean. Prod."},{"key":"10.1016\/j.compchemeng.2026.109672_b29","series-title":"International Cross-Domain Conference for Machine Learning and Knowledge Extraction","first-page":"77","article-title":"Explainable reinforcement learning: A survey","author":"Puiutta","year":"2020"},{"issue":"268","key":"10.1016\/j.compchemeng.2026.109672_b30","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.compchemeng.2026.109672_b31","series-title":"Explainable reinforcement learning via temporal policy decomposition","author":"Ruggeri","year":"2025"},{"key":"10.1016\/j.compchemeng.2026.109672_b32","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"10.1016\/j.compchemeng.2026.109672_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.artint.2020.103367","article-title":"Interestingness elements for explainable reinforcement learning: Understanding agents\u2019 capabilities and limitations","volume":"288","author":"Sequeira","year":"2020","journal-title":"Artificial Intelligence"},{"key":"10.1016\/j.compchemeng.2026.109672_b34","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.compchemeng.2019.05.029","article-title":"Reinforcement learning\u2013overview of recent progress and implications for process control","volume":"127","author":"Shin","year":"2019","journal-title":"Comput. Chem. Eng."},{"issue":"8","key":"10.1016\/j.compchemeng.2026.109672_b35","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1038\/s42256-023-00692-8","article-title":"Explaining machine learning models with interactive natural language conversations using TalkToModel","volume":"5","author":"Slack","year":"2023","journal-title":"Nat. Mach. Intell."},{"issue":"15","key":"10.1016\/j.compchemeng.2026.109672_b36","doi-asserted-by":"crossref","first-page":"12534","DOI":"10.1021\/jacs.4c17738","article-title":"A multiagent-driven robotic ai chemist enabling autonomous chemical research on demand","volume":"147","author":"Song","year":"2025","journal-title":"J. Am. Chem. Soc."},{"key":"10.1016\/j.compchemeng.2026.109672_b37","doi-asserted-by":"crossref","DOI":"10.1016\/j.compchemeng.2024.108849","article-title":"Resilience-based explainable reinforcement learning in chemical process safety","volume":"191","author":"Szatm\u00e1ri","year":"2024","journal-title":"Comput. Chem. Eng."},{"key":"10.1016\/j.compchemeng.2026.109672_b38","series-title":"ECAI 2024","first-page":"2790","article-title":"Explaining an agent\u2019s future beliefs through temporally decomposing future reward estimators","author":"Towers","year":"2024"},{"key":"10.1016\/j.compchemeng.2026.109672_b39","series-title":"Contrastive explanations for reinforcement learning in terms of expected consequences","author":"van der Waa","year":"2018"},{"key":"10.1016\/j.compchemeng.2026.109672_b40","series-title":"2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","first-page":"1","article-title":"Verbal explanations for deep reinforcement learning neural networks with attention on extracted features","author":"Wang","year":"2019"},{"key":"10.1016\/j.compchemeng.2026.109672_b41","series-title":"Model-agnostic policy explanations with large language models","author":"Xi-Jia","year":"2025"},{"key":"10.1016\/j.compchemeng.2026.109672_b42","first-page":"18375","article-title":"What did you think would happen? explaining agent behaviour through intended outcomes","volume":"33","author":"Yau","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.compchemeng.2026.109672_b43","series-title":"International Conference on Machine Learning","first-page":"1899","article-title":"Graying the black box: Understanding dqns","author":"Zahavy","year":"2016"},{"issue":"2","key":"10.1016\/j.compchemeng.2026.109672_b44","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1109\/TCSS.2021.3096824","article-title":"Explainable AI in deep reinforcement learning models for power system emergency control","volume":"9","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Comput. Soc. Syst."}],"container-title":["Computers & Chemical Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0098135426001250?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0098135426001250?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T23:29:12Z","timestamp":1778714952000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0098135426001250"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":44,"alternative-id":["S0098135426001250"],"URL":"https:\/\/doi.org\/10.1016\/j.compchemeng.2026.109672","relation":{},"ISSN":["0098-1354"],"issn-type":[{"value":"0098-1354","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"TalkToAgent: A multi-agent LLM Framework for natural language explanation of reinforcement learning policies","name":"articletitle","label":"Article Title"},{"value":"Computers & Chemical Engineering","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.compchemeng.2026.109672","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":"109672"}}