{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T08:09:25Z","timestamp":1779178165779,"version":"3.51.4"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2023JJ50047"],"award-info":[{"award-number":["2023JJ50047"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010083","name":"Hunan Provincial Innovation Foundation for Postgraduate","doi-asserted-by":"publisher","award":["CX20251718"],"award-info":[{"award-number":["CX20251718"]}],"id":[{"id":"10.13039\/501100010083","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Special Project of the 4th Hunan Tourism Development Conference","award":["HS2001911520"],"award-info":[{"award-number":["HS2001911520"]}]},{"name":"Academic Degree and Postgraduate Education Teaching Reform Research Project","award":["YJG2025A003"],"award-info":[{"award-number":["YJG2025A003"]}]},{"name":"Research and Practice Project of Science Communication of Hunan Province","award":["kxcbkt2025066"],"award-info":[{"award-number":["kxcbkt2025066"]}]},{"name":"Research and Practice Project of Science Communication of Hunan Province","award":["2026JJ30106"],"award-info":[{"award-number":["2026JJ30106"]}]},{"DOI":"10.13039\/100009110","name":"Natural Science Foundation of Xinjiang Uygur Autonomous Region","doi-asserted-by":"publisher","award":["2026JJ80260"],"award-info":[{"award-number":["2026JJ80260"]}],"id":[{"id":"10.13039\/100009110","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s10489-026-07270-6","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T07:49:18Z","timestamp":1779176958000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A reinforcement learning decision-making method with multi-granularity semantic prompts from large language models"],"prefix":"10.1007","volume":"56","author":[{"given":"Shilin","family":"Hao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9654-4798","authenticated-orcid":false,"given":"Gang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaotian","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,19]]},"reference":[{"issue":"3","key":"7270_CR1","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1007\/s10586-024-04893-7","volume":"28","author":"AA Ismail","year":"2025","unstructured":"Ismail AA, Khalifa NE, El-Khoribi RA (2025) A survey on resource scheduling approaches in multi-access edge computing environment: a deep reinforcement learning study. Clust Comput 28(3):184","journal-title":"Clust Comput"},{"key":"7270_CR2","doi-asserted-by":"publisher","first-page":"109193","DOI":"10.1016\/j.compeleceng.2024.109193","volume":"116","author":"P Liu","year":"2024","unstructured":"Liu P, Ma X, Ding J, Gu C (2024) Multi-agent collaborative path planning algorithm with reinforcement learning and combined prioritized experience replay in Internet of Things. Comput Electr Eng 116:109193","journal-title":"Comput Electr Eng"},{"issue":"1","key":"7270_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-023-10620-2","volume":"57","author":"X Wang","year":"2024","unstructured":"Wang X et al (2024) Deep reinforcement learning-based air combat maneuver decision-making: literature review, implementation tutorial and future direction. Artif Intell Rev 57(1):1","journal-title":"Artif Intell Rev"},{"key":"7270_CR4","doi-asserted-by":"crossref","unstructured":"Xu P et\u00a0al (2025) Exploration via embracing diversity in reinforcement learning for sparse-reward procedurally-generated tasks. IEEE Trans Syst Man Cybernet Syst","DOI":"10.1109\/TSMC.2025.3574024"},{"key":"7270_CR5","first-page":"25502","volume":"34","author":"D Ghosh","year":"2021","unstructured":"Ghosh D et al (2021) Why generalization in RL is difficult: Epistemic POMDPs and implicit partial observability. Adv Neural Inf Process Syst 34:25502\u201325515","journal-title":"Adv Neural Inf Process Syst"},{"key":"7270_CR6","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1613\/jair.1.13743","volume":"75","author":"RZ Liu","year":"2022","unstructured":"Liu RZ et al (2022) On efficient reinforcement learning for full-length game of StarCraft II. J Artif Intell Res 75:213\u2013260","journal-title":"J Artif Intell Res"},{"issue":"3","key":"7270_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3641289","volume":"15","author":"Y Chang","year":"2024","unstructured":"Chang Y et al (2024) A survey on evaluation of large language models. ACM Trans Intell Syst Technol 15(3):1\u201345","journal-title":"ACM Trans Intell Syst Technol"},{"key":"7270_CR8","doi-asserted-by":"crossref","unstructured":"Valmeekam K et\u00a0al (2023) On the planning abilities of large language models: A critical investigation. In: Advances in neural information processing systems 36:75993\u201376005","DOI":"10.52202\/075280-3320"},{"issue":"5","key":"7270_CR9","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1007\/s11370-024-00550-5","volume":"17","author":"Y Kim","year":"2024","unstructured":"Kim Y et al (2024) A survey on integration of large language models with intelligent robots. Intel Serv Robot 17(5):1091\u20131107","journal-title":"Intel Serv Robot"},{"key":"7270_CR10","unstructured":"Brohan A et\u00a0al (2023) Do as I can, not as I say: Grounding language in robotic affordances. In: Conference on robot learning, pp 287\u2013318"},{"key":"7270_CR11","unstructured":"Hu H, Sadigh D (2023) Language instructed reinforcement learning for human-AI coordination. In: International conference on machine learning, pp 13584\u201313598"},{"key":"7270_CR12","doi-asserted-by":"crossref","unstructured":"Cao Y et\u00a0al (2024) Survey on large language model-enhanced reinforcement learning: Concept, taxonomy, and methods. IEEE Trans Neural Netw Learn Syst","DOI":"10.1109\/TNNLS.2024.3497992"},{"key":"7270_CR13","unstructured":"Nachum O et\u00a0al (2018) Data-efficient hierarchical reinforcement learning. In: Advances in neural information processing systems 31"},{"key":"7270_CR14","doi-asserted-by":"publisher","unstructured":"Ma Y et\u00a0al (2023) Rethinking decision transformer via hierarchical reinforcement learning. https:\/\/doi.org\/10.48550\/arXiv.2311.00267","DOI":"10.48550\/arXiv.2311.00267"},{"key":"7270_CR15","doi-asserted-by":"publisher","unstructured":"Huang S et\u00a0al (2024) In-context decision transformer: Reinforcement learning via hierarchical chain-of-thought. https:\/\/doi.org\/10.48550\/arXiv.2405.20692","DOI":"10.48550\/arXiv.2405.20692"},{"key":"7270_CR16","doi-asserted-by":"crossref","unstructured":"Wang Z, Wang H, Qi Y (2025) Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance. In: ACM web conference companion, pp 520\u2013529","DOI":"10.1145\/3701716.3715233"},{"key":"7270_CR17","doi-asserted-by":"crossref","unstructured":"Ouyang Q et\u00a0al (2023) Enhancing accuracy in large language models through dynamic real-time information injection. Preprints","DOI":"10.20944\/preprints202312.1987.v1"},{"key":"7270_CR18","unstructured":"Espeholt L et\u00a0al (2018) IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures. In: International conference on machine learning, pp 1407\u20131416"},{"key":"7270_CR19","doi-asserted-by":"crossref","unstructured":"Hu S et\u00a0al (2024) On transforming reinforcement learning with transformers: The development trajectory. IEEE Trans Pattern Anal Mach Intell","DOI":"10.1109\/TPAMI.2024.3408271"},{"key":"7270_CR20","doi-asserted-by":"crossref","unstructured":"Oh JH et\u00a0al (2024) Bimanual long-horizon manipulation via temporal-context transformer RL. IEEE Robot Automation Lett","DOI":"10.1109\/LRA.2024.3484167"},{"key":"7270_CR21","unstructured":"Huang W et\u00a0al (2026) Inner Monologue: Embodied Reasoning through Planning with Language Models. In: Conference on robot learning, pp 1769\u20131782"},{"key":"7270_CR22","doi-asserted-by":"crossref","unstructured":"Wei J et\u00a0al (2022) Chain-of-thought prompting elicits reasoning in large language models. In: Advances in neural information processing systems 35:24824\u201324837","DOI":"10.52202\/068431-1800"},{"key":"7270_CR23","doi-asserted-by":"publisher","unstructured":"Chen Z et\u00a0al (2024) AutoPRM: Automating procedural supervision for multi-step reasoning via controllable question decomposition. https:\/\/doi.org\/10.18653\/v1\/2024.naacl-long.73","DOI":"10.18653\/v1\/2024.naacl-long.73"},{"key":"7270_CR24","unstructured":"Xu M et\u00a0al (2022) Prompting decision transformer for few-shot policy generalization. In: International conference on machine learning, pp 24631\u201324645"},{"key":"7270_CR25","doi-asserted-by":"crossref","unstructured":"Li B et\u00a0al (2021) Hierarchical learning from demonstrations for long-horizon tasks. In: IEEE international conference on robotics and automation, pp 4545\u20134551","DOI":"10.1109\/ICRA48506.2021.9561408"},{"key":"7270_CR26","doi-asserted-by":"crossref","unstructured":"Lu K et\u00a0al (2024) Learning generalizable manipulation policy with adapter-based parameter fine-tuning. In: IEEE\/RSJ international conference on intelligent robots and systems, pp 13510\u201313517","DOI":"10.1109\/IROS58592.2024.10801544"},{"key":"7270_CR27","unstructured":"Yao S et\u00a0al (2023) ReAct: Synergizing reasoning and acting in language models. In: International conference on learning representations"},{"key":"7270_CR28","doi-asserted-by":"publisher","unstructured":"Li Z et\u00a0al (2024) LLM-PySC2: StarCraft II learning environment for large language models. https:\/\/doi.org\/10.48550\/arXiv.2411.05348","DOI":"10.48550\/arXiv.2411.05348"},{"key":"7270_CR29","unstructured":"Yu T et\u00a0al (2020) MOPO: Model-based offline policy optimization. In: Advances in neural information processing systems 33:14129\u201314142"},{"key":"7270_CR30","doi-asserted-by":"crossref","unstructured":"Ma H et\u00a0al (2024) Coevolving with the other you: Fine-tuning LLM with sequential cooperative multi-agent reinforcement learning. In: Advances in neural information processing systems 37:15497\u201315525","DOI":"10.52202\/079017-0495"},{"key":"7270_CR31","doi-asserted-by":"crossref","unstructured":"Shinn N et\u00a0al (2023) Reflexion: Language agents with verbal reinforcement learning. In: Advances in neural information processing systems 36:8634\u20138652","DOI":"10.52202\/075280-0377"},{"key":"7270_CR32","doi-asserted-by":"crossref","unstructured":"Ouyang L et\u00a0al (2022) Training language models to follow instructions with human feedback. In: Advances in neural information processing systems 35:27730\u201327744","DOI":"10.52202\/068431-2011"},{"key":"7270_CR33","unstructured":"Ma W, Mi Q, Zeng Y, Yan X, Wu Y, Lin R et\u00a0al (2024) Large Language Models Play StarCraft II: Benchmarks and a Chain of Summarization Approach. In: Advances in neural information processing systems"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-026-07270-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-026-07270-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-026-07270-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T07:49:34Z","timestamp":1779176974000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-026-07270-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":33,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["7270"],"URL":"https:\/\/doi.org\/10.1007\/s10489-026-07270-6","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,19]]},"assertion":[{"value":"16 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"263"}}