Toward Agentic AI: Generative Information Retrieval Inspired Intelligent Communications and Networking

TL;DR

This work addresses intelligent decision-making in telecom networks by integrating agentic AI with generative information retrieval. It surveys retrieval strategies (traditional, hybrid, semantic, knowledge-based, and agentic contextual) and introduces an agentic contextual retrieval framework that combines multi-source knowledge, structured reasoning, and self-validation. A case-study-style simulation demonstrates that the framework improves answer accuracy, explanation consistency, and retrieval efficiency over baselines. The work highlights future directions including security/privacy, energy efficiency, and network-aware adaptation, underscoring practical impact for 3GPP-aligned autonomous networking.

Abstract

The increasing complexity and scale of modern telecommunications networks demand intelligent automation to enhance efficiency, adaptability, and resilience. Agentic AI has emerged as a key paradigm for intelligent communications and networking, enabling AI-driven agents to perceive, reason, decide, and act within dynamic networking environments. However, effective decision-making in telecom applications, such as network planning, management, and resource allocation, requires integrating retrieval mechanisms that support multi-hop reasoning, historical cross-referencing, and compliance with evolving 3GPP standards. This article presents a forward-looking perspective on generative information retrieval-inspired intelligent communications and networking, emphasizing the role of knowledge acquisition, processing, and retrieval in agentic AI for telecom systems. We first provide a comprehensive review of generative information retrieval strategies, including traditional retrieval, hybrid retrieval, semantic retrieval, knowledge-based retrieval, and agentic contextual retrieval. We then analyze their advantages, limitations, and suitability for various networking scenarios. Next, we present a survey about their applications in communications and networking. Additionally, we introduce an agentic contextual retrieval framework to enhance telecom-specific planning by integrating multi-source retrieval, structured reasoning, and self-reflective validation. Experimental results demonstrate that our framework significantly improves answer accuracy, explanation consistency, and retrieval efficiency compared to traditional and semantic retrieval methods. Finally, we outline future research directions.

Figures (4)

• Figure 1: Overview of key retrieval strategies in networking. The figure highlights the methodologies, key components, and applications of different approaches, including traditional retrieval, hybrid retrieval, semantic retrieval, knowledge-based retrieval, and agentic contextual retrieval.
• Figure 2: A summary of recent retrieval methods in communications and networking, which provides an overview of various proposals, research scenarios, and levels of human-AI interaction.
• Figure 3: Illustration of the agentic contextual retrieval enhanced intelligent base station for troubleshooting and decision-making. The framework follows a structured four-step workflow: (A) Query understanding and reformulation ensure alignment with 3GPP terminology using LLM-based query expansion. (B) Multi-source knowledge retrieval extracts relevant information from both structured (e.g., 3GPP standards) and unstructured (e.g., online sources) datasets. (C) Contextual evidence aggregation and reasoning synthesize retrieved knowledge into structured responses using chain-of-thought reasoning. (D) Decision-making and self-validation enhance accuracy through confidence-based verification and iterative refinement, reducing hallucinations and improving response consistency.
• Figure 4: Performance comparison of Agentic Contextual Retrieval against baseline methods, including QWen-Max without retriever, traditional retrieval, and semantic retrieval.