{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:24:50Z","timestamp":1785857090004,"version":"3.56.0"},"reference-count":162,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Mobile Information Networks\u2013National Science and Technology Major Project of China","award":["2025ZD1304800"],"award-info":[{"award-number":["2025ZD1304800"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Commun. Surv. Tutorials"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/comst.2026.3712862","type":"journal-article","created":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:08:43Z","timestamp":1783973323000},"page":"6665-6693","source":"Crossref","is-referenced-by-count":1,"title":["Tutorial on Large Language Model-Enhanced Reinforcement Learning for Wireless Networks"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8774-2769","authenticated-orcid":false,"given":"Lingyi","family":"Cai","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjie","family":"Fu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxi","family":"Huang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6859-3645","authenticated-orcid":false,"given":"Ruichen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University","place":["Jurong West, Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6198-3712","authenticated-orcid":false,"given":"Yinqiu","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University","place":["Jurong West, Singapore"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8218-3490","authenticated-orcid":false,"given":"Jiawen","family":"Kang","sequence":"additional","affiliation":[{"name":"Guangdong University of Technology","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4440-941X","authenticated-orcid":false,"given":"Zehui","family":"Xiong","sequence":"additional","affiliation":[{"name":"Queen\u2019s University Belfast","place":["Belfast, U.K."]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8482-1046","authenticated-orcid":false,"given":"Tao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology","place":["Wuhan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4890-0748","authenticated-orcid":false,"given":"Xianbin","family":"Wang","sequence":"additional","affiliation":[{"name":"Western University","place":["London, ON, Canada"],"department":["Department of Electrical and Computer Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7052-0007","authenticated-orcid":false,"given":"Shiwen","family":"Mao","sequence":"additional","affiliation":[{"name":"Auburn University","place":["Auburn, USA"],"department":["Department of Electrical and Computer Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4140-287X","authenticated-orcid":false,"given":"Xuemin","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Waterloo","place":["Waterloo, ON, Canada"],"department":["Department of Electrical and Computer Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3435752"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3459037"},{"key":"ref4","first-page":"104922","article-title":"LLM at network edge: A layer-wise efficient federated fine-tuning approach","volume-title":"Proc. 39th Annu. Conf. Neural Inf. Process. Syst","volume":"38","author":"Shen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2176"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3511662"},{"key":"ref7","first-page":"46534","article-title":"Self-refine: Iterative refinement with self-feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"36","author":"Madaan"},{"key":"ref8","article-title":"Large language model-enhanced reinforcement learning for low-altitude economy networking","author":"Cai","year":"2025","journal-title":"arXiv:2505.21045"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3063822"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3323344"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2020.3015386"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3469547"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3438543"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3361534"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118397"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2025.3581912"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3584698"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2025.3612760"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.016.2300547"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3347580"},{"key":"ref21","first-page":"35663","article-title":"Text2Reward: Reward shaping with language models for reinforcement learning","volume-title":"Proc. 12th Int. Conf. Learn. Represent","volume":"2024","author":"Xie"},{"key":"ref22","first-page":"26516","article-title":"Eureka: Human-level reward design via coding large language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent","volume":"2024","author":"Ma"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3401159"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3497992"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3553843"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3025365"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3073036"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3160697"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2020.3035898"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2935201"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3325843"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3641289"},{"key":"ref34","article-title":"Chain-of-thought for large language model-empowered wireless communications","author":"Wang","year":"2025","journal-title":"arXiv:2505.22320"},{"key":"ref35","first-page":"55734","article-title":"Large language model as attributed training data generator: A tale of diversity and bias","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yu"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3240707"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3327596"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3391767"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref40","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref41","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3323554"},{"key":"ref43","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref44","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3051163"},{"key":"ref46","article-title":"ORAN-GUIDE: RAG-driven prompt learning for LLM-augmented reinforcement learning in O-RAN network slicing","author":"Lotfi","year":"2025","journal-title":"arXiv:2506.00576"},{"key":"ref47","article-title":"Aero-LLM: A distributed framework for secure UAV communication and intelligent decision-making","author":"Dharmalingam","year":"2025","journal-title":"arXiv:2502.05220"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3452591"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3616864"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3435558"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2025.3541078"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref53","first-page":"1877","volume-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"issue":"140","key":"ref56","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref57","article-title":"The LLAMA 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC61545.2025.10978505"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.005.2400019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657767"},{"key":"ref61","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"35","author":"Wei"},{"key":"ref62","first-page":"53764","article-title":"WISE: Rethinking the knowledge memory for lifelong model editing of large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"37","author":"Wang"},{"key":"ref63","first-page":"26311","article-title":"Do embodied agents dream of pixelated sheep: Embodied decision making using language guided world modelling","volume-title":"Proc. 40th Int. Conf. Mach. Learn","volume":"202","author":"Nottingham"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890371"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC59896.2024.10555960"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3712678.3721880"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2025.3539638"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2400526"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2500384"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2024.3405397"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3497923"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3625468.3653068"},{"key":"ref73","volume-title":"A Google Congestion Control Algorithm for Real-Time Communication. Internet-Draft Draft-ietf-RMCAT-GCC-02","author":"Holmer","year":"2016"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.016.2300600"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.300"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1038\/s44459-025-00015-w"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN61024.2024.00041"},{"key":"ref78","first-page":"1","article-title":"Rlaif vs. RLHF: Scaling reinforcement learning from human feedback with ai feedback","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Lee"},{"issue":"1","key":"ref79","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.jnca.2011.08.007","article-title":"Reinforcement learning for context awareness and intelligence in wireless networks: Review, new features and open issues","volume":"35","author":"Yau","year":"2012","journal-title":"J. Netw. Comput. Appl."},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2957778"},{"key":"ref82","first-page":"1","article-title":"Agent in the sky: Intelligent multi-agent framework for autonomous haps coordination and real-world event adaptation","volume-title":"Proc. AAAI Workshop Artif. Intell. Wireless Commun. Netw. (AI4WCN)","author":"Han"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3615410"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3564163"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2026.3669346"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3540820"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3524612"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2262"},{"key":"ref89","first-page":"1","article-title":"Next-GPT: Any-to-any multimodal LLM","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802322"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-006-9184-9"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29936"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511750854"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3232366"},{"issue":"2","key":"ref95","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","volume":"1","author":"Hu"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2863960"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/tse.2026.3657432"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3204794"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3182119"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1787"},{"key":"ref101","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.ins.2022.05.053","article-title":"Multi-objective workflow scheduling based on genetic algorithm in cloud environment","volume":"606","author":"Xia","year":"2022","journal-title":"Inf. Sci."},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2025.3529082"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2021.3076514"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/3760390"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-95-0014-7_37"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.276"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TMLCN.2025.3593184"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC65185.2026.11555128"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2025.3584656"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops63917.2026.11586683"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS67624.2025.00046"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/MSN60784.2023.00093"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3645168"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops67674.2025.11162457"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS65812.2025.11152884"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2024.10582827"},{"key":"ref118","article-title":"Leveraging large language models for DRL-based anti-jamming strategies in zero touch networks","author":"Ali","year":"2023","journal-title":"arXiv:2308.09376"},{"key":"ref119","first-page":"4956","article-title":"DreamerPro: Reconstruction-free model-based reinforcement learning with prototypical representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Deng"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.03.037"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9839123"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2023.3306039"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.3390\/s22114157"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref126","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Lewis"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2016.2521718"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2011.5934929"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278776"},{"key":"ref131","first-page":"1244","article-title":"Deep black-box reinforcement learning with movement primitives","volume-title":"Proc. Conf. Robot Learn.","author":"Otto"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57321-8_5"},{"key":"ref133","first-page":"29992","article-title":"Learning to model the world with language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2935"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3186893"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3240690"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2024.3493375"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3451215"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01846"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2025.3634768"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2025.3586868"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2024.3404391"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-09459-0"},{"key":"ref145","article-title":"A survey of energy efficient methods for UAV communication","volume":"41","author":"Jin","year":"2023","journal-title":"Veh. Commun."},{"key":"ref146","first-page":"5829","article-title":"Exploration-guided reward shaping for reinforcement learning under sparse rewards","volume-title":"Proc. 36th Conf. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Devidze"},{"key":"ref147","article-title":"Some fundamental aspects about Lipschitz continuity of neural networks","volume-title":"Proc. 12th Int. Conf. Learn. Represent","author":"Khromov"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3165227"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2025.3644352"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2026.3658670"},{"key":"ref151","first-page":"7968","article-title":"Improving generalization in reinforcement learning with mixture regularization","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"33","author":"Wang"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref153","first-page":"5556","article-title":"Controlling overestimation bias with truncated mixture of continuous distributional quantile critics","volume-title":"Proc. 37th Int. Conf. Mach. Learn","volume":"119","author":"Kuznetsov"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3582864"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2026.3668817"},{"key":"ref156","article-title":"Repurposing backdoors for good: Ephemeral intrinsic proofs for verifiable aggregation in cross-silo federated learning","author":"Qin","year":"2026","journal-title":"arXiv:2603.10692"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/mcom.001.2500584"},{"key":"ref158","article-title":"LLM agent communication protocol (LACP) requires urgent standardization: A telecom-inspired protocol is necessary","volume-title":"Proc. NeurIPS Workshop: AI ML Next-Generation Wireless Commun. Netw","author":"Li"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/TMLCN.2025.3592658"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3400011"},{"key":"ref161","article-title":"Federated agentic AI for wireless networks: Fundamentals, approaches, and applications","author":"Cai","year":"2026","journal-title":"arXiv:2603.01755"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2026.3660010"}],"container-title":["IEEE Communications Surveys & Tutorials"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9739\/11321210\/11606384.pdf?arnumber=11606384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T19:09:52Z","timestamp":1784833792000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11606384\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":162,"URL":"https:\/\/doi.org\/10.1109\/comst.2026.3712862","relation":{},"ISSN":["1553-877X","2373-745X"],"issn-type":[{"value":"1553-877X","type":"electronic"},{"value":"2373-745X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}