RAG-Enabled Intent Reasoning for Application-Network Interaction

2025-05-14

AI Summary

Intent-Driven Networking (IBN) faces challenges in translating natural-language user intents into structured network configurations due to semantic heterogeneity across diverse applications, resulting in poor translation accuracy and limited scalability. Method: This paper proposes Intent-RAG—a context-aware AI translation framework that synergistically integrates Machine Reasoning (MR) and Retrieval-Augmented Generation (RAG). It employs explicit reasoning chains to verify semantic consistency and mitigate large language model (LLM) hallucinations, while incorporating a domain-adapted retrieval module to support both generic and customized intent expressions. Contribution/Results: Experiments demonstrate that Intent-RAG significantly outperforms baseline LLMs and standard RAG across multi-domain intent parsing tasks, achieving breakthrough improvements in accuracy, generalization, and cross-domain scalability. The framework establishes a novel paradigm for semantic-level network autonomy in IBN, enabling true “say-and-get” user experience.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Cognitive Robotics
• Natural Language Processing: Safety and Robustness

Application Category

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

Abstract

Intent-based network (IBN) is a promising solution to automate network operation and management. IBN aims to offer human-tailored network interaction, allowing the network to communicate in a way that aligns with the network users' language, rather than requiring the network users to understand the technical language of the network/devices. Nowadays, different applications interact with the network, each with its own specialized needs and domain language. Creating semantic languages (i.e., ontology-based languages) and associating them with each application to facilitate intent translation lacks technical expertise and is neither practical nor scalable. To tackle the aforementioned problem, we propose a context-aware AI framework that utilizes machine reasoning (MR), retrieval augmented generation (RAG), and generative AI technologies to interpret intents from different applications and generate structured network intents. The proposed framework allows for generalized/domain-specific intent expression and overcomes the drawbacks of large language models (LLMs) and vanilla-RAG framework. The experimental results show that our proposed intent-RAG framework outperforms the LLM and vanilla-RAG framework in intent translation.

Problem

• Automating intent-based network interaction for diverse applications
• Overcoming limitations of manual semantic language creation
• Improving intent translation accuracy beyond LLMs and vanilla-RAG

Innovation

• Uses machine reasoning for intent interpretation
• Integrates retrieval augmented generation technology
• Leverages generative AI for structured intent generation