CoChat
Sign Up
Cited by 75Advanced Wireless Communication TechnologiesAdvanced Data and IoT TechnologiesArtificial Intelligence Applications

The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.

From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communications

Open access
Jiang, Feibo, Pan, Cunhua, Wang, Kezhi, Michiardi, Pietro, Dobre, Octavia A., Debbah, Merouane·2026·IEEE Journal on Selected Areas in Communications
DOI 10.1109/jsac.2026.3660010
Open this paper in CoChat — free accountOpen PDF

Abstract

With the advent of 6G communications, intelligent communication systems face multiple challenges, including constrained perception and response capabilities, limited scalability, and low adaptability in dynamic environments. To address these challenges, this tutorial provides a systematic and comprehensive introduction to the principles, design, and applications of Large Artificial Intelligence Models (LAMs) and Agentic AI technologies in intelligent communication systems, aiming to offer researchers an integrated overview of cutting-edge methodologies and practical insights. First, the tutorial outlines the background of 6G communications and reviews the technological evolution from LAMs to Agentic AI. It then systematically examines the key components required for constructing LAMs, classifies various types of LAMs, and analyzes their applicability in communication. A LAM-centric design paradigm tailored for communication systems is subsequently proposed, encompassing dataset construction, internal learning, and external learning approaches. Building upon this foundation, the tutorial develops an LAM-based Agentic AI system for intelligent communications, elaborating on its core components—including agents, world models, planners, knowledge bases, tools, and memory modules— as well as their interaction mechanisms. Finally, it provides an in-depth review of representative applications of LAMs and Agentic AI in communication scenarios, and summarizes the current research challenges and future directions, with the goal of fostering the development of efficient, secure, and sustainable next-generation intelligent communication systems.

Overview

Integrity signals

Registry

Crossref · 10.1109/jsac.2026.3660010

Cites

0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

The publisher hasn’t deposited this paper’s reference list.

Research works printed but not linked: 205

  1. Alliance, 2024, ITU-R framework for IMT-2030: Review and future direction, 1
  2. 10.1109/MVT.2019.2921208 · DOI · Paper page
  3. 10.1162/tacl_a_00349 · DOI · Paper page
  4. Radford, 2019, Language models are unsupervised multitask learners, OpenAI Blog, 1, 9
  5. Shirish Keskar, 2019, CTRL: A conditional transformer language model for controllable generation, arXiv:1909.05858 · arXiv
  6. Raffel, 2019, Exploring the limits of transfer learning with a unified text-to-text transformer, J. Mach. Learn. Res., 21, 1
  7. Ouyang, Training language models to follow instructions with human feedback, 27730
  8. 10.1109/ICCV51070.2023.00371 · DOI · Paper page
  9. Achiam, 2023, GPT-4 technical report, arXiv:2303.08774 · arXiv
  10. Team, 2023, Gemini: A family of highly capable multimodal models, arXiv:2312.11805 · arXiv
  11. Guo, 2025, DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning, arXiv:2501.12948 · arXiv
  12. Yang, 2023, Auto-GPT for online decision making: Benchmarks and additional opinions, arXiv:2306.02224 · arXiv
  13. Shen, HuggingGPT: Solving AI tasks with ChatGPT and its friends in hugging face, 38154
  14. Xie, 2023, OpenAgents: An open platform for language agents in the wild, arXiv:2310.10634 · arXiv
  15. Amine Ferrag, 2025, From LLM reasoning to autonomous AI agents: A comprehensive review, arXiv:2504.19678 · arXiv
  16. 10.1109/ACCESS.2025.3532853 · DOI · Paper page
  17. Gridach, 2025, Agentic AI for scientific discovery: A survey of progress, challenges, and future directions, arXiv:2503.08979 · arXiv
  18. 10.1109/comst.2026.3660844 · DOI
  19. 10.1109/COMST.2024.3465447 · DOI
  20. 10.1109/COMST.2025.3564333 · DOI
  21. Gao, 2025, Agentic satellite-augmented low-altitude economy and terrestrial networks: A survey on generative approaches, arXiv:2507.14633 · arXiv
  22. 10.1109/COMST.2025.3576176 · DOI
  23. Sapkota, 2025, UAVs meet agentic AI: A multidomain survey of autonomous aerial intelligence and agentic UAVs, arXiv:2506.08045 · arXiv
  24. 10.1109/OJCOMS.2020.3010270 · DOI
  25. 10.1109/MWC.016.2300600 · DOI
  26. 10.1109/MWC.001.2300346 · DOI
  27. 10.1109/WACVW60836.2024.00131 · DOI
  28. 10.1109/MCOM.001.2300550 · DOI
  29. 10.18653/v1/2025.acl-long.1383 · DOI
  30. 10.48550/ARXIV.1706.03762 · DOI · Paper page
  31. 10.1109/ICASSP49357.2023.10094735 · DOI
  32. Leng, 2025, Unveiling the power of complex-valued transformers in wireless communications, arXiv:2502.11151 · arXiv
  33. 10.52953/JWRA8095 · DOI
  34. 10.1109/MWC.007.2400124 · DOI
  35. Dosovitskiy, 2020, An image is worth 16 × 16 words: Transformers for image recognition at scale, arXiv:2010.11929 · arXiv
  36. 10.1109/ICCWorkshops67674.2025.11162294 · DOI
  37. 10.1109/ACCESS.2024.3460480 · DOI
  38. 10.3390/rs16224204 · DOI
  39. 10.48550/arXiv.1312.6114 · DOI · Paper page
  40. 10.1109/WCNC51071.2022.9771642 · DOI
  41. 10.1109/TCOMM.2024.3386577 · DOI
  42. 10.1016/j.prime.2023.100335 · DOI
  43. Sohl-Dickstein, Deep unsupervised learning using nonequilibrium thermodynamics, 2256
  44. Ho, Denoising diffusion probabilistic models, 6840
  45. 10.1109/CVPR52688.2022.01042 · DOI · Paper page
  46. Betker, 2023, Improving image generation with better captions, Comput. Sci., 2, 8
  47. Saharia, Photorealistic text-to-image diffusion models with deep language understanding, 36479
  48. 10.1016/j.dsp.2025.105283 · DOI
  49. 10.1109/ICASSP48485.2024.10447612 · DOI
  50. 10.1109/ICC51166.2024.10622730 · DOI
  51. 10.3390/electronics13112063 · DOI
  52. Liu, 2024, Sora: A review on background, technology, limitations, and opportunities of large vision models, arXiv:2402.17177 · arXiv
  53. 10.1162/neco.1991.3.1.79 · DOI · Paper page
  54. Du, GLaM: Efficient scaling of language models with mixture-of-experts, 5547
  55. Jiang, 2024, Mixtral of experts, arXiv:2401.04088 · arXiv
  56. 10.1109/MWC.001.2400150 · DOI
  57. 10.1109/JSAC.2024.3459037 · DOI
  58. Gao, 2023, MoE-AMC: Enhancing automatic modulation classification performance using Mixture-of-Experts, arXiv:2312.02298 · arXiv
  59. 10.1109/MCOM.001.2300575 · DOI
  60. 10.1016/j.hcc.2024.100211 · DOI · Paper page
  61. 10.1109/CVPR52688.2022.01553 · DOI · Paper page
  62. Oquab, 2023, DINOv2: Learning robust visual features without supervision, arXiv:2304.07193 · arXiv
  63. Jiang, 2025, Lightweight vision model-based multi-user semantic communication systems, arXiv:2502.16424 · arXiv
  64. 10.1109/MNET.2024.3435752 · DOI
  65. Team, 2024, Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context, arXiv:2403.05530 · arXiv
  66. Liu, Visual instruction tuning, 36, 34892
  67. 10.1007/978-3-031-72775-7_2 · DOI
  68. Xu, LLaVA-UHD: An LMM perceiving any aspect ratio and high-resolution images, 390
  69. 10.1109/LWC.2024.3429295 · DOI
  70. 10.1109/MNET.2024.3427313 · DOI
  71. Kawamoto, 2023, Application of frozen large-scale models to multimodal task-oriented dialogue, arXiv:2310.00845 · arXiv
  72. Ghasemi, 2024, A comprehensive survey of reinforcement learning: From algorithms to practical challenges, arXiv:2411.18892 · arXiv
  73. 10.1145/3777411 · DOI
  74. Wei, Chain-of-thought prompting elicits reasoning in large language models, 35, 24824
  75. Lewis, Retrieval-augmented generation for knowledge-intensive NLP tasks, 33, 9459
  76. Shao, 2024, DeepSeekMath: Pushing the limits of mathematical reasoning in open language models, arXiv:2402.03300 · arXiv
  77. Yang, 2024, Qwen2.5 technical report, arXiv:2412.15115 · arXiv
  78. 10.1007/978-3-540-75538-8_7 · DOI
  79. Qu, 2025, A survey of efficient reasoning for large reasoning models: Language, multimodality, and beyond, arXiv:2503.21614 · arXiv
  80. 10.18653/v1/2023.emnlp-main.298 · DOI · Paper page
  81. Shazeer, 2019, Fast transformer decoding: One write-head is all you need, arXiv:1911.02150 · arXiv
  82. Zhang, 2024, TinyLlama: An open-source small language model, arXiv:2401.02385 · arXiv
  83. 10.18653/v1/2025.naacl-long.253 · DOI
  84. Hu, 2024, MiniCPM: Unveiling the potential of small language models with scalable training strategies, arXiv:2404.06395 · arXiv
  85. Javaheripi, 2023, Phi-2: The surprising power of small language models, Microsoft Res. Blog, 1, 3
  86. Abdin, 2024, Phi-3 technical report: A highly capable language model locally on your phone, arXiv:2404.14219 · arXiv
  87. 10.1109/MWC.015.2300404 · DOI
  88. 10.1109/TMLCN.2025.3593184 · DOI
  89. 10.1109/GCWkshp64532.2024.11101012 · DOI
  90. 10.1109/MCOM.001.2500111 · DOI
  91. 10.1016/j.dcan.2024.10.010 · DOI
  92. Li, 2021, A channel coding benchmark for meta-learning, arXiv:2107.07579 · arXiv
  93. Alkhateeb, 2019, DeepMIMO: A generic deep learning dataset for millimeter wave and massive MIMO applications, arXiv:1902.06435 · arXiv
  94. 10.1145/3448016.3457550 · DOI
  95. 10.14445/22315381/IJETT-V73I2P125 · DOI
  96. Zhao, 2025, Edge general intelligence through world models and agentic AI: Fundamentals, solutions, and challenges, arXiv:2508.09561 · arXiv
  97. Jaech, 2024, OpenAI o1 system card, arXiv:2412.16720 · arXiv
  98. Yao, Tree of thoughts: Deliberate problem solving with large language models, 36, 11809
  99. 10.1609/aaai.v38i16.29720 · DOI · Paper page
  100. 10.18653/v1/2023.acl-long.147 · DOI · Paper page
  101. Gao, 2023, Retrieval-augmented generation for large language models: A survey, arXiv:2312.10997 · arXiv
  102. 10.1109/TKDE.2024.3352100 · DOI · Paper page
  103. Sahoo, 2024, A systematic survey of prompt engineering in large language models: Techniques and applications, arXiv:2402.07927 · arXiv
  104. Ehtesham, 2025, A survey of agent interoperability protocols: Model context protocol (MCP), agent communication protocol (ACP), agent-to-agent protocol (A2A), and agent network protocol (ANP), arXiv:2505.02279 · arXiv
  105. 10.1007/s11704-024-40678-2 · DOI
  106. 10.1016/j.procir.2021.03.088 · DOI
  107. Ma, 2023, A comprehensive survey on vector database: Storage and retrieval technique, challenge, arXiv:2310.11703 · arXiv
  108. 10.1109/ICMLA52953.2021.00105 · DOI
  109. Shinn, Reflexion: Language agents with verbal reinforcement learning, 8634
  110. 10.1109/MNET.2025.3579496 · DOI
  111. 10.1109/MWC.2025.3596934 · DOI
  112. Tong, 2025, WirelessAgent: Large language model agents for intelligent wireless networks, arXiv:2505.01074 · arXiv
  113. Yang, 2025, Agentic web: Weaving the next web with AI agents, arXiv:2507.21206 · arXiv
  114. Wang, 2025, Internet of Agents: Fundamentals, applications, and challenges, arXiv:2505.07176 · arXiv
  115. Haseeb, 2025, Context engineering for multi-agent LLM code assistants using elicit, NotebookLM, ChatGPT, and claude code, arXiv:2508.08322 · arXiv
  116. 10.1109/JSAC.2025.3623167 · DOI
  117. Wang, 2024, Large-language-model enabled semantic communication systems, arXiv:2407.14112 · arXiv
  118. 10.1109/MWC.002.2300460 · DOI
  119. 10.1109/ISCC65549.2025.11326061 · DOI
  120. Ribouh, 2025, Large language model-based semantic communication system for image transmission, arXiv:2501.12988 · arXiv
  121. 10.1109/tvt.2025.3595688 · DOI
  122. 10.1109/TWC.2025.3553851 · DOI
  123. 10.1109/TWC.2025.3539526 · DOI
  124. 10.1109/TWC.2025.3624573 · DOI
  125. 10.1109/ICCWorkshops59551.2024.10615340 · DOI
  126. 10.1109/MWC.001.2500056 · DOI
  127. 10.1109/TMC.2025.3607717 · DOI
  128. 10.1109/JSAC.2025.3610398 · DOI
  129. 10.1109/MCOM.002.2400106 · DOI · Paper page
  130. 10.1145/3680207.3723486 · DOI
  131. 10.1109/JIOT.2024.3470210 · DOI
  132. Otoum, 2025, LLM-based threat detection and prevention framework for IoT ecosystems, arXiv:2505.00240 · arXiv
  133. 10.1007/s43926-024-00083-4 · DOI
  134. 10.1007/978-3-031-78666-2_11 · DOI
  135. 10.1016/j.patter.2025.101429 · DOI
  136. Mo, 2024, IoT-LM: Large multisensory language models for the Internet of Things, arXiv:2407.09801 · arXiv
  137. 10.1109/MCOM.001.2400076 · DOI
  138. 10.1145/3649329.3658473 · DOI
  139. 10.1109/JIOT.2024.3524255 · DOI
  140. 10.1109/ICCCWorkshops62562.2024.10693742 · DOI
  141. 10.1109/COMST.2025.3527641 · DOI
  142. 10.1109/GLOBECOM52923.2024.10901542 · DOI
  143. 10.1109/MCOM.001.2400764 · DOI
  144. 10.1109/OJCOMS.2024.3456549 · DOI
  145. 10.23919/JCIN.2023.10272352 · DOI · Paper page
  146. 10.1109/GCWkshps58843.2023.10465211 · DOI
  147. 10.1109/ICAIIC64266.2025.10920709 · DOI
  148. 10.1145/3626111.3628183 · DOI
  149. 10.1109/ACCESS.2025.3625637 · DOI
  150. 10.1145/3651890.3672268 · DOI · Paper page
  151. Dandoush, 2024, Large language models meet network slicing management and orchestration, arXiv:2403.13721 · arXiv
  152. 10.1145/3696348.3696868 · DOI
  153. 10.1109/MNET.2024.3367788 · DOI
  154. Ali Khowaja, 2024, Pathway to secure and trustworthy ZSM for LLMs: Attacks, defense, and opportunities, arXiv:2408.00722 · arXiv
  155. Luo, 2023, BC4LLM: Trusted artificial intelligence when blockchain meets large language models, arXiv:2310.06278 · arXiv
  156. 10.1609/aaai.v38i19.30136 · DOI
  157. 10.18653/v1/2025.acl-long.532 · DOI
  158. Wang, 2023, PrivateLoRA for efficient privacy preserving LLM, arXiv:2311.14030 · arXiv
  159. 10.3390/ai5040134 · DOI
  160. 10.1186/s42400-025-00361-w · DOI · Paper page
  161. 10.1016/j.jnlest.2025.100301 · DOI
  162. Lee, 2024, LLM-empowered resource allocation in wireless communications systems, arXiv:2408.02944 · arXiv
  163. 10.1109/IWCMC61514.2024.10592370 · DOI
  164. Peng, 2025, LLM-OptiRA: LLM-driven optimization of resource allocation for non-convex problems in wireless communications, arXiv:2505.02091 · arXiv
  165. Ren, 2024, Retrieval-augmented generation for mobile edge computing via large language model, arXiv:2412.20820 · arXiv
  166. Xu, 2024, Cached model-as-a-resource: Provisioning large language model agents for edge intelligence in Space-air-ground integrated networks, arXiv:2403.05826 · arXiv
  167. Yang, 2024, PerLLM: Personalized inference scheduling with edge-cloud collaboration for diverse LLM services, arXiv:2405.14636 · arXiv
  168. 10.1145/3641512.3686358 · DOI
  169. Jiang, D-LLM: A token adaptive computing resource allocation strategy for large language models, 1725
  170. Amayuelas, 2025, Self-resource allocation in multi-agent LLM systems, arXiv:2504.02051 · arXiv
  171. 10.1109/MNET.2024.3470774 · DOI
  172. 10.1109/MNET.2024.3422309 · DOI · Paper page
  173. 10.1109/GCWkshp64532.2024.11101226 · DOI
  174. 10.1109/MWC.005.2400019 · DOI
  175. 10.1109/TWC.2024.3519325 · DOI
  176. 10.1109/MWC.002.2400332 · DOI
  177. 10.1109/ISCTech63666.2024.10845514 · DOI
  178. 10.1109/MWC.008.2200504 · DOI
  179. 10.1109/VTC2024-Fall63153.2024.10757470 · DOI
  180. 10.1109/INFOCOMWKSHPS65812.2025.11152722 · DOI
  181. Arda Onsu, 2024, Leveraging edge intelligence and LLMs to advance 6G-enabled Internet of Automated Defense Vehicles, arXiv:2501.06205 · arXiv
  182. 10.1109/JSAC.2025.3560042 · DOI
  183. 10.1109/ITSC58415.2024.10919532 · DOI
  184. 10.3390/drones9030213 · DOI
  185. 10.3390/s25010175 · DOI
  186. Sautenkov, 2025, UAV-CodeAgents: Scalable UAV mission planning via multi-agent ReAct and vision-language reasoning, arXiv:2505.07236 · arXiv
  187. 10.1002/aaai.12087 · DOI
  188. Yu, 2024, Recent advances of multimodal continual learning: A comprehensive survey, arXiv:2410.05352 · arXiv
  189. Ru, 2024, Maintaining adversarial robustness in continuous learning, arXiv:2402.11196 · arXiv
  190. 10.1007/978-3-030-01252-6_33 · DOI · Paper page
  191. 10.3390/encyclopedia3020049 · DOI
  192. Lightman, Let’s verify step by step, 1
  193. Xi, 2024, Training large language models for reasoning through reverse curriculum reinforcement learning, arXiv:2402.05808 · arXiv
  194. 10.1109/TAI.2022.3150264 · DOI
  195. Wagner, 2021, Neural-symbolic integration for interactive learning and conceptual grounding, arXiv:2112.11805 · arXiv
  196. 10.18653/v1/N16-3020 · DOI · Paper page
  197. Bau, 2018, GAN dissection: Visualizing and understanding generative adversarial networks, arXiv:1811.10597 · arXiv
  198. 10.1162/tacl_a_00704 · DOI · Paper page
  199. Xiao, SmoothQuant: Accurate and efficient post-training quantization for large language models, 38087
  200. Xu, 2024, A survey on knowledge distillation of large language models, arXiv:2402.13116 · arXiv

200 of 205 shown

Cited by

Sorted by citations

Related

Metadata

Authors
Jiang, F., Pan, C., Wang, K., Michiardi, P., Dobre, O. A., & Debbah, M.
Affiliations
  • Hunan Normal University (CN)
  • Southeast University (CN)
  • Brunel University of London (GB)
  • Data Science Department, EURECOM, Biot, France
  • Memorial University of Newfoundland (CA)
  • Khalifa University of Science and Technology (AE)
ORCID
Venue
IEEE Journal on Selected Areas in Communications
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2026
Volume
44
Pages
3507-3540
ISSN
  • 0733-8716 (ISSN-L)
  • 1558-0008
DOI
10.1109/jsac.2026.3660010
OpenAlex
W7127083419
Cited by
53
References
0
Citations by year
2026: 48
FWCI
78.25
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Journal on Selected Areas in Communications (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Brunel University Research Archive (BURA) (Brunel University London) (submittedVersion, other-oa)
  • arXiv (Cornell University)
Funders
  • National Natural Science Foundation of China (62572184)
  • Natural Science Foundation of Hunan Province (2024JJ5270, 2025JJ50365)
  • Changsha Natural Science Foundation (kq2402098 and Grant kq2402162)
Topics
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Communication Technologies
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Data and IoT Technologies
  • Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
Keywords
agentic AI, intelligent communication systems, 6G communication, world models, knowledge base, memory modules, dataset construction, next-generation communication systems

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review