{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T06:56:50Z","timestamp":1781679410579,"version":"3.54.5"},"reference-count":53,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neucom.2026.133945","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T06:52:41Z","timestamp":1779173561000},"page":"133945","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["DyCoT-RE: Chain-of-Thought-enhanced LLM reward engineering with dual-dynamic optimization for reinforcement learning"],"prefix":"10.1016","volume":"695","author":[{"given":"Xinning","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinxin","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longfei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7556-1940","authenticated-orcid":false,"given":"Lunde","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133945_bib0005","series-title":"Reinforcement Learning: An Introduction","volume":"vol. 1","author":"Sutton","year":"1998"},{"key":"10.1016\/j.neucom.2026.133945_bib0010","author":"Amodei"},{"key":"10.1016\/j.neucom.2026.133945_bib0015","first-page":"517","article-title":"Misspecification in inverse reinforcement learning","volume":"73","author":"Skalse","year":"2022","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.neucom.2026.133945_bib0020","article-title":"Reward learning from human preferences and demonstrations in atari","volume":"31","author":"Ibarz","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133945_bib0025","article-title":"Inverse reward design","volume":"30","author":"Hadfield-Menell","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133945_bib0030","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133945_bib0035","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133945_bib0040","author":"Nguyen"},{"key":"10.1016\/j.neucom.2026.133945_bib0045","author":"Peeperkorn"},{"key":"10.1016\/j.neucom.2026.133945_bib0050","series-title":"Proceedings of the International Conference on Machine Learning (ICML)","first-page":"287","article-title":"Switch transformers: scaling to trillion parameter models with simple and efficient sparsity","author":"Fedus","year":"2022"},{"key":"10.1016\/j.neucom.2026.133945_bib0055","series-title":"International Conference on Machine Learning","first-page":"5712","article-title":"GLaM: efficient scaling of language models with mixture-of-experts","author":"Du","year":"2022"},{"key":"10.1016\/j.neucom.2026.133945_bib0060","author":"Huang"},{"key":"10.1016\/j.neucom.2026.133945_bib0065","author":"Qi"},{"key":"10.1016\/j.neucom.2026.133945_bib0070","series-title":"2025 10th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA)","first-page":"222","article-title":"LLM-based reward engineering for reinforcement learning: a chain of thought approach","author":"Zhu","year":"2025"},{"key":"10.1016\/j.neucom.2026.133945_bib0075","series-title":"ICML, 99","first-page":"278","article-title":"Policy invariance under reward transformations: theory and application to reward shaping","author":"Ng","year":"1999"},{"issue":"2","key":"10.1016\/j.neucom.2026.133945_bib0080","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/TAMD.2010.2051031","article-title":"Intrinsically motivated reinforcement learning: an evolutionary perspective","volume":"2","author":"Singh","year":"2010","journal-title":"IEEE Trans. Auton. Ment. Dev."},{"key":"10.1016\/j.neucom.2026.133945_bib0085","author":"Burda"},{"key":"10.1016\/j.neucom.2026.133945_bib0090","author":"Kwon"},{"key":"10.1016\/j.neucom.2026.133945_bib0095","author":"Yu"},{"key":"10.1016\/j.neucom.2026.133945_bib0100","author":"Xie"},{"key":"10.1016\/j.neucom.2026.133945_bib0105","author":"Rocamonde"},{"key":"10.1016\/j.neucom.2026.133945_bib0110","author":"Shen"},{"key":"10.1016\/j.neucom.2026.133945_bib0115","author":"Ma"},{"key":"10.1016\/j.neucom.2026.133945_bib0120","article-title":"Reward guidance for reinforcement learning tasks based on large language models: the LMGT framework","volume":"310","author":"Deng","year":"2025","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.neucom.2026.133945_bib0125","author":"Sun"},{"key":"10.1016\/j.neucom.2026.133945_bib0130","author":"Sarukkai"},{"key":"10.1016\/j.neucom.2026.133945_bib0135","unstructured":"T. Simonds, K. Lopez, A. Yoshiyama, D. Garmier, RLSR: reinforcement learning from self reward, arXiv preprint arXiv:2505.08827, 2025."},{"key":"10.1016\/j.neucom.2026.133945_bib0140","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133945_bib0145","first-page":"24824","article-title":"Chain-of-Thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133945_bib0150","author":"Wang"},{"key":"10.1016\/j.neucom.2026.133945_bib0155","series-title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD \u201925), 1","first-page":"2584","article-title":"Struct-X: enhancing the reasoning capabilities of large language models in structured data scenarios","author":"Tan","year":"2025"},{"key":"10.1016\/j.neucom.2026.133945_bib0165","author":"Shum"},{"issue":"c","key":"10.1016\/j.neucom.2026.133945_bib0170","article-title":"A novel prompting method for few-shot NER via LLMs","volume":"8","author":"Cheng","year":"2024","journal-title":"Natural Language Processing Journal"},{"key":"10.1016\/j.neucom.2026.133945_bib0175","author":"Baek"},{"key":"10.1016\/j.neucom.2026.133945_bib0180","author":"Cheng"},{"key":"10.1016\/j.neucom.2026.133945_bib0185","author":"Nakkiran"},{"key":"10.1016\/j.neucom.2026.133945_bib0190","author":"Shojaee"},{"key":"10.1016\/j.neucom.2026.133945_bib0195","author":"Yin"},{"key":"10.1016\/j.neucom.2026.133945_bib0200","author":"Mirzadeh"},{"key":"10.1016\/j.neucom.2026.133945_bib0205","author":"Tan"},{"key":"10.1016\/j.neucom.2026.133945_bib0210","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, 38","first-page":"437","article-title":"Hot or cold? Adaptive temperature sampling for code generation with large language models","author":"Zhu","year":"2024"},{"key":"10.1016\/j.neucom.2026.133945_bib0215","author":"Zhang"},{"key":"10.1016\/j.neucom.2026.133945_bib0220","author":"Cecere"},{"key":"10.1016\/j.neucom.2026.133945_bib0225","author":"Chang"},{"key":"10.1016\/j.neucom.2026.133945_bib0230","first-page":"7103","article-title":"Mixture-of-experts with expert choice routing","volume":"35","author":"Zhou","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133945_bib0235","author":"Li"},{"key":"10.1016\/j.neucom.2026.133945_bib0240","author":"Hu"},{"key":"10.1016\/j.neucom.2026.133945_bib0245","author":"Li"},{"key":"10.1016\/j.neucom.2026.133945_bib0250","author":"Towers"},{"key":"10.1016\/j.neucom.2026.133945_bib0255","author":"Schulman"},{"issue":"268","key":"10.1016\/j.neucom.2026.133945_bib0260","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.neucom.2026.133945_bib0265","author":"Haarnoja"},{"key":"10.1016\/j.neucom.2026.133945_bib0270","series-title":"International Conference on Machine Learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226013421?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226013421?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T06:36:09Z","timestamp":1781678169000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226013421"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":53,"alternative-id":["S0925231226013421"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133945","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"DyCoT-RE: Chain-of-Thought-enhanced LLM reward engineering with dual-dynamic optimization for reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133945","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133945"}}