In this paper, we propose an Agentic Artificial Intelligence (AI) framework for wireless networks. The framework coordinates a pool of AI agents guided by Natural Language (NL) inputs from a human operator. At its core, the super agent is powered by a Hierarchical Online Decision Transformer (H-ODT). It orchestrates three categories of agents: (i) inter-slice, intra-slice resource allocation agents, (ii) network application orchestration agents, and (iii) self-healing agents. The orchestration takes place with the help of an Agentic Retrieval-Augmented Generation (RAG) module that integrates knowledge from heterogeneous sources. In this proposed methodology, the super agent directly interfaces with operators and generates sequential policies to activate relevant agents. The proposed framework is evaluated against three state-of-the-art baselines, showing improved throughput, reduced network delay, and higher energy efficiency at both slice-level and system-wide performance metrics. Also, the proposed Agentic framework introduces a bi-level human operator intent validation methodology, both at the slice-level and Key Performance Indicator (KPI)-level using generative AI-based time series predictors. We could rule out performance-degrading operator intents with an accuracy of 88.5%. Lastly, while being interrupted by any performance-degrading events, the self-healing capability of Agentic AI in our framework automatically recovers 90% of its previous performance, avoiding quality-of-service drifts when there is no human involvement.

翻译：本文提出了一种面向无线网络的代理人工智能（AI）框架。该框架协调一组由人类操作员提供的自然语言（NL）输入引导的AI代理。其核心是采用分层在线决策Transformer（H-ODT）驱动的超级代理，该代理负责编排三类代理：（i）跨切片与切片内资源分配代理、（ii）网络应用编排代理以及（iii）自愈代理。编排过程借助集成异构知识源的代理检索增强生成（RAG）模块实现。在所提方法中，超级代理直接与操作员交互，生成序列化策略以激活相关代理。我们基于三种最先进的基线方法评估了该框架，结果显示在切片级和系统级性能指标上，该框架均实现了更高的吞吐量、更低的网络延迟及更高的能效。同时，该代理框架引入了一种双层人类操作员意图验证方法，在切片级和关键性能指标（KPI）级利用基于生成式AI的时间序列预测器进行验证。该方法能以88.5%的准确率排除会导致性能下降的操作员意图。最后，当遭遇任何性能下降事件时，框架中代理AI的自愈能力可自动恢复90%的先前性能，从而在无人工干预的情况下避免服务质量漂移。