1.中信科移动通信技术股份有限公司,北京 100085
2.大唐移动通信设备有限公司,北京 100083
3.无线移动通信全国重点实验室(电信科学技术研究院有限公司),北京 100191
李紫燕(2001- ),女,电信科学技术研究院硕士生,中信科移动通信技术股份有限公司预研工程师,主要研究方向为网络架构、人工智能、意图驱动网络等。
谷肖飞(1994- ),男,大唐移动通信设备有限公司标准工程师,主要从事6G 标准、AI、用户面及本地服务接入等方向的技术研究工作。
李慧欣(1997- ),女,大唐移动通信设备有限公司研究工程师,主要从事6G、AI 等技术研究和移动通信网络大模型实现等相关工作。
王亚鹏(1985- ),女,大唐移动通信设备有限公司工程师,主要从事6G、算力网络、集群通信等的技术研究、标准化推进工作。
艾明(1974- ),男,博士,中信科移动通信技术股份有限公司正高级工程师,主要从事网络架构、卫星互联网、位置服务、智能化等研究工作。
收稿:2026-02-28,
修回:2026-03-20,
录用:2026-04-09,
网络首发:2026-07-21,
纸质出版:2026-06-20
移动端阅览
李紫燕,谷肖飞,李慧欣等.面向6G核心网的内生智能体架构与意图驱动子网生成机制[J].电信科学,2026,42(06):52-65.
Li Ziyan,Gu Xiaofei,Li Huixin,et al.Endogenous intelligent agent architecture and intent-driven subnetwork generation mechanism for 6G core networks[J].Telecommunications Science,2026,42(06):52-65.
李紫燕,谷肖飞,李慧欣等.面向6G核心网的内生智能体架构与意图驱动子网生成机制[J].电信科学,2026,42(06):52-65. DOI: 10.11959/j.issn.1000-0801.DXKX260132.
Li Ziyan,Gu Xiaofei,Li Huixin,et al.Endogenous intelligent agent architecture and intent-driven subnetwork generation mechanism for 6G core networks[J].Telecommunications Science,2026,42(06):52-65. DOI: 10.11959/j.issn.1000-0801.DXKX260132.
为实现IMT-2030(6G)的普惠智能愿景,提出了一种具有多智能体协同特征的内生智能核心网架构。基于服务化架构(service-based architecture,SBA),通过定义意图接口(AI-enhanced intent function,AIEF)、智能体控制功能(agent control function,ACF)与智能体注册与管理功能(agent registration and management function,ARMF)等核心网络功能,构建了面向6G场景的内生智能网络架构。为验证该架构的可行性,选取意图驱动子网生成任务作为典型任务,搭建了整体系统验证平台,验证了所提架构下的注册、编排及用户设备(user equipment,UE)接入功能。针对6G逻辑子网的构建需求,设计了由ACF全程协调保障的两阶段多智能体协同的子网生成机制,并在单卡RTX4090D下开展仿真实验与性能评估工作。验证结果表明,所提架构与机制可实现基于自然语言的意图表达到子网实例生成的完整闭环,证实了未来网络中引入AI智能体实现网络内生智能化的可行性。
To realize the ubiquitous intelligence vision of IMT-2030 (6G)
an endogenous intelligent core network architecture with multi-agent collaboration was proposed. Based on the service-based architecture (SBA)
the AI-enhanced intent function (AIEF)
agent control function (ACF)
and agent registration and management function (ARMF) were defined to support endogenous intelligence in 6G networks. An intent-driven subnet generation task was selected to verify the proposed architecture
and a system platform was developed to validate registration
orchestration
and user equipment (UE) access.For 6G logical subnet construction
a two-stage multi-agent collaborative mechanism coordinated by the ACF was designed and evaluated on a single NVIDIA RTX 4090D GPU. The results demonstrate the feasibility of AI-agent-enabled endogenous intelligence for future networks.
ITU-D SG2 Q2/2 Workshop. Framework and overall objectives of the future development of IMT for 2030 and beyond [R ] . 2024 .
崔琪楣 , 尤肖虎 , 倪巍 , 等 . 面向6G网络的AI与通信融合探析: 基础、挑战与未来研究机遇 [J ] . 中国科学: 信息科学 , 2026 , 56 ( 1 ): 241 - 242 .
Cui Q M , You X H , Ni W , et al . Overview of AI and communication for 6G network: fundamentals, challenges, and future research opportunities [J ] . Scientia Sinica (Informationis) , 2026 , 56 ( 1 ): 241 - 242 .
朱威 , 马田丰 , 金友兴 , 等 . 智能体互联网潜在关键技术展望 [J ] . 信息通信技术 , 2025 , 19 ( 5 ): 48 - 54 .
Zhu W , Ma T F , Jin Y X , et al . Outlook on potential key technologies for Internet of agents [J ] . Information and Communications Technologies , 2025 , 19 ( 5 ): 48 - 54 .
中国移动通信研究院 . 智能体通信网络(ACN)白皮书(2024年) [R ] . 2024 .
CMRI . AI-agent communication network white paper(2024) [R ] . 2024 .
Wang L , Ma C , Feng X Y , et al . A survey on large language model based autonomous agents [J ] . Frontiers of Computer Science , 2024 , 18 ( 6 ): 186345 .
Yao S Y , Zhao J , Yu D , et al . ReAct: synergizing reasoning and acting in language models [PP ] . V1. arXiv ( 2022-10-06 )[ 2026-01-20 ] . arXiv: 2210.03629 .
Wang G , Xie Y , Jiang Y , et al . Voyager: an open-ended embodied agent with large language models [PP ] . V2. arXiv ( 2023-10-19 )[ 2026-01-12 ] . arXiv: 2305.16291 .
Ghanem B , Hammoud H , Itani H , et al . CAMEL: communicative agents for “mind”exploration of large language model society [C ] // Proceedings of the Advances in Neural Information Processing Systems 36 . San Diego, California : NeurIPS , 2023 : 51991 - 52008 .
Xu M R , Niyato D , Kang J W , et al . When large language model agents meet 6G networks: perception, grounding, and alignment [J ] . IEEE Wireless Communications , 2024 , 31 ( 6 ): 63 - 71 .
3GPP. Study on architecture for 6G system(Stage 2):TR 23.801-01 V0.3.0 [R ] . 2025 .
3GPP. KI#18-AI for 6G architecture [R ] . 2026 .
3GPP. KI#19: Solution variants [R ] . 2026 .
刘海涛 , 谌丽 , 康绍莉 , 等 . 面向6G网络融合的以用户为中心关键技术 [J ] . 无线电通信技术 , 2024 , 50 ( 3 ): 453 - 460 .
Liu H T , Chen L , Kang S L , et al . User-centric key technologies towards 6G converged network [J ] . Radio Communications Technology , 2024 , 50 ( 3 ): 453 - 460 .
CATT . CATT initial views on 6G Core [C ] // Proceedings of the 3GPP Workshop on 6G . 2025 : 1 - 7 .
段晓东 , 黄正磊 , 陆璐 , 等 . 智能体通信网络赋能新型服务供给和网络架构演进 [J ] . 通信世界 , 2025 ( 24 ): 5 - 6 .
Duan X D , Huang Z L , Lu L , et al . Agent communication network enables new service supply and network architecture evolution [J ] . Communications World , 2025 ( 24 ): 5 - 6 .
段晓东 , 黄正磊 , 陆璐 , 等 . 智能体通信网络(ACN): 面向6G的网络发展新范式 [J ] . 通信学报 , 2025 , 46 ( 11 ): 332 - 346 .
Duan X D , Huang Z L , Lu L , et al . AI agent communication network(ACN): a new network paradigm for 6G [J ] . Journal on Communications , 2025 , 46 ( 11 ): 332 - 346 .
张培龙 , 马云潇 , 李华 , 等 . 大语言模型驱动的多智能体网络意图识别框架 [J ] . 小型微型计算机系统 , 2026 : 1 - 10 .
Zhang P L , Ma Y X , Li H , et al . Large language model driven multi-agents for network intent recognition framework [J ] . Journal of Chinese Computer Systems , 2026 : 1 - 10 .
Ma X L , Zhao R Q , Liu Y , et al . Design of a large language model for improving customer service in telecom operators [J ] . Electronics Letters , 2024 , 60 ( 10 ): e13218 .
0
浏览量
47
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621