KP-A: A Unified Network Knowledge Plane for Catalyzing Agentic Network Intelligence

2025-07-10

AI Summary

To address data redundancy and semantic inconsistency arising from isolated knowledge retrieval pipelines for intelligent tasks in 6G autonomous networks, this paper proposes KP-A—the first unified knowledge plane tailored for agent-based network intelligence. KP-A decouples knowledge acquisition from intelligent logic execution, standardizes knowledge interfaces based on the Open-RAN service model, and integrates large language models with a multi-agent collaborative architecture to enable end-to-end knowledge extraction, unified storage, and API-driven dynamic querying. It further supports edge AI service orchestration. Experimental evaluation demonstrates KP-A’s effectiveness in real-world network knowledge question-answering and edge service orchestration scenarios. The implementation is open-sourced, providing a reproducible foundation for research and contributing to the standardization of intelligent 6G networks.

Technology Category

• Knowledge Representation and Reasoning: Knowledge Acquisition
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Data Mining & Knowledge Management: Knowledge Acquisition from the Web

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The emergence of large language models (LLMs) and agentic systems is enabling autonomous 6G networks with advanced intelligence, including self-configuration, self-optimization, and self-healing. However, the current implementation of individual intelligence tasks necessitates isolated knowledge retrieval pipelines, resulting in redundant data flows and inconsistent interpretations. Inspired by the service model unification effort in Open-RAN (to support interoperability and vendor diversity), we propose KP-A: a unified Network Knowledge Plane specifically designed for Agentic network intelligence. By decoupling network knowledge acquisition and management from intelligence logic, KP-A streamlines development and reduces maintenance complexity for intelligence engineers. By offering an intuitive and consistent knowledge interface, KP-A also enhances interoperability for the network intelligence agents. We demonstrate KP-A in two representative intelligence tasks: live network knowledge Q&A and edge AI service orchestration. All implementation artifacts have been open-sourced to support reproducibility and future standardization efforts.

Problem

• Eliminates redundant data flows in autonomous 6G networks
• Decouples knowledge acquisition from intelligence logic
• Enhances interoperability for network intelligence agents

Innovation

• Unified Network Knowledge Plane for agentic intelligence
• Decouples knowledge acquisition from intelligence logic
• Provides intuitive consistent knowledge interface