智能体 AI 赋能 6G 意图驱动网络
Agentic AI Empowered Intent-Based Networking for 6G
AI 导读
一篇 arXiv 论文提出面向 6G 网络的分层多智能体框架，用基于 LLM 的智能体通过 ReAct 循环将自然语言意图分解并生成网络切片配置。系统由编排器协调 RAN 与 Core Network 两个专家智能体，实验显示其性能优于单一智能体、规则系统和直接 LLM 提示，架构原则适用于 O-RAN 部署。研究表明，需通过结构化提示词工程编码领域决策阈值与运营策略，才能实现可靠的网络自动化。
正文 · 原文
Abstract:The transition towards sixth-generation (6G) wireless networks necessitates autonomous orchestration mechanisms capable of translating high-level operational intents into executable network configurations. Existing approaches to Intent-Based Networking (IBN) rely upon either rule-based systems that struggle with linguistic variation or end-to-end neural models that lack interpretability and fail to enforce operational constraints. This paper presents a hierarchical multi-agent framework where Large Language Model (LLM) based agents autonomously decompose natural language intents, consult domain-specific specialists, and synthesise technically feasible network slice configurations through iterative reasoning-acting (ReAct) cycles. The proposed architecture employs an orchestrator agent coordinating two specialist agents, namely Radio Access Network (RAN) and Core Network agents, via ReAct-style reasoning, grounded in structured network state representations. Experimental evaluation across diverse benchmark scenarios demonstrates that the proposed system outperforms monolithic agents, rule-based systems, and direct LLM prompting, with architectural principles applicable to Open RAN (O-RAN) deployments. The results also demonstrate that whilst contemporary LLMs possess substantial general telecommunications knowledge, structured prompt engineering encoding domain-specific decision thresholds and operational policies is essential for reliable network automation performance.
| Comments: | Submitted for Possible Journal Publication |
| Subjects: | Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI) |
| Cite as: | arXiv:2601.06640 [cs.AI] |
| (or arXiv:2601.06640v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2601.06640 arXiv-issued DOI via DataCite |
Submission history
From: Kezhi Wang [view email]
[v1]
Sat, 10 Jan 2026 17:49:40 UTC (422 KB)
[v2]
Mon, 26 Oct 2026 14:29:53 UTC (312 KB)
来源：arXiv cs.AI · arxiv.org