{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:15:09Z","timestamp":1784736909776,"version":"3.55.0"},"reference-count":67,"publisher":"Zhejiang University Press","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front Inform Technol Electron Eng"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1631\/fitee.2400468","type":"journal-article","created":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T07:11:45Z","timestamp":1741158705000},"page":"278-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Adaptive layer splitting for wireless large language model inference in edge computing: a model-based reinforcement learning approach","\u57fa\u4e8e\u6a21\u578b\u5f3a\u5316\u5b66\u4e60\u7684\u8fb9\u7f18\u8ba1\u7b97\u65e0\u7ebf\u5927\u8bed\u8a00\u6a21\u578b\u63a8\u7406\u81ea\u9002\u5e94\u5c42\u5207\u5206\u65b9\u6cd5"],"prefix":"10.1631","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9570-2000","authenticated-orcid":false,"given":"Yuxuan","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-5060","authenticated-orcid":false,"given":"Rongpeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1098-7589","authenticated-orcid":false,"given":"Xiaoxue","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhifeng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1492-1364","authenticated-orcid":false,"given":"Honggang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"635","published-online":{"date-parts":[[2025,3,5]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/jiot.2017.2750180"},{"key":"ref2","author":"Bai","year":"2022","journal-title":"Training a helpful and harmless assistant with reinforcement learning from human feedback"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2004.841555"},{"key":"ref4","article-title":"Language models are few-shot learners","volume-title":"Proc 34th Int Conf on Neural Information Processing Systems","author":"Brown","year":"2020"},{"key":"ref5","author":"Chen","year":"2024","journal-title":"The landscape and challenges of HPC research and LLMs"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/jsac.2021.3118346"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/mnet.2024.3376419"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1979.10481038"},{"key":"ref9","first-page":"465","article-title":"PILCO: a model-based and data-efficient approach to policy search","volume-title":"Proc 28th Int Conf on Machine Learning","author":"Deisenroth","year":"2011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3638550.3641126"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.65109\/ZYEH4087"},{"key":"ref12","year":"2023","journal-title":"Gemini: a family of highly capable multimodal models"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2018.05.003"},{"key":"ref14","author":"Gupta","year":"2024","journal-title":"Introducing Prem-1B"},{"key":"ref15","author":"Hadi","year":"2023","journal-title":"A survey on large language models: applications, challenges, limitations, and practical usage"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2023.103989"},{"key":"ref17","author":"Jiang","year":"2023","journal-title":"Mistral 7B"},{"key":"ref18","author":"Jin","year":"2024","journal-title":"Health-LLM: personalized retrieval-augmented disease prediction system"},{"key":"ref19","author":"Kaddour","year":"2023","journal-title":"Challenges and applications of large language models"},{"key":"ref20","author":"Kaiser","year":"2019","journal-title":"Model-based reinforcement learning for Atari"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.measen.2022.100409"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2022.07.009"},{"key":"ref23","author":"Lan","year":"2021","journal-title":"Progressive feature transmission for split inference at the wireless edge"},{"key":"ref24","author":"Le Scao","year":"2022","journal-title":"BLOOM: a 176B-parameter open-access multilingual language model"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/lcomm.2023.3269769"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/jsac.2021.3126076"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2019.2946140"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2022.3173057"},{"key":"ref29","author":"Li","year":"2017","journal-title":"Deep reinforcement learning: an overview"},{"key":"ref30","author":"Lin","year":"2024","journal-title":"Infinite-LLM: efficient LLM service for long context with DistAttention and distributed KVCache"},{"key":"ref31","author":"Lin","year":"2024a","journal-title":"Pushing large language models to the 6G edge: vision, challenges, and opportunities"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/mwc.014.2300319"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/mnet.001.1900517"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2019.2916583"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2017.2682318"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/comst.2017.2745201"},{"key":"ref37","author":"Merity","year":"2016","journal-title":"Pointer sentinel mixture models"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref39","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc 33rdInt Conf on Machine Learning","author":"Mnih","year":"2016"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-08-009306-2.50005-4"},{"key":"ref42","author":"Nijkamp","year":"2022","journal-title":"CodeGen: an open large language model for code with multi-turn program synthesis"},{"key":"ref43","article-title":"Efficient Distributed LLM Inference with Dynamic Partitioning","volume-title":"Technical Report UCB\/EECS-2024-108, California, USA","author":"Ong","year":"2024"},{"key":"ref44","year":"2023","journal-title":"GPT-4 Technical Report, San Francisco, USA"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/app14052074"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3001277"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.23919\/jcin.2019.8917870"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2023.3294494"},{"key":"ref49","first-page":"674","article-title":"Reward estimation for variance reduction in deep reinforcement learning","volume-title":"Proc 2ndConf on Robot Learning","author":"Romoff","year":"2018"},{"key":"ref50","author":"Rozi\u00e8re","year":"2023","journal-title":"Code LLAMA: open foundation models for code"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/imcom53663.2022.9721798"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/mprv.2009.82"},{"key":"ref53","author":"Schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref54","author":"Shlezinger","year":"2021","journal-title":"Model-based machine learning for communications"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1974.tb00994.x"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"ref57","author":"Touvron","year":"2023","journal-title":"LLAMA 2: open foundation and fine-tuned chat models"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.845"},{"key":"ref59","author":"Wang","year":"2023","journal-title":"OpenChat: advancing open-source language models with mixed-quality data"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/iccc57788.2023.10233330"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-023-01659-w"},{"key":"ref62","author":"Wei","year":"2021","journal-title":"Finetuned language models are zero-shot learners"},{"key":"ref63","author":"Wu","year":"2023","journal-title":"BloombergGPT: a large language model for finance"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2024.3395624"},{"key":"ref65","volume":"2024","author":"Zhang","journal-title":"EdgeShard: efficient LLM inference via collaborative edge computing"},{"key":"ref66","author":"Zhang","year":"2023","journal-title":"Wider and deeper LLM networks are fairer LLM evaluators"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2022.107658"}],"container-title":["Frontiers of Information Technology & Electronic Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2400468.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1631\/FITEE.2400468\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2400468.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T06:37:16Z","timestamp":1771655836000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1631\/FITEE.2400468"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":67,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["468"],"URL":"https:\/\/doi.org\/10.1631\/fitee.2400468","relation":{},"ISSN":["2095-9184","2095-9230"],"issn-type":[{"value":"2095-9184","type":"print"},{"value":"2095-9230","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2]]},"assertion":[{"value":"1 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 September 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Honggang ZHANG is a guest editor of this special issue; he was not involved with the peer review process of this paper. All the authors declare that they have no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}