Intent-Based Management provides a shift in network management by automating the alignment of network operations with business objectives. However, primary challenges include: 1) intent processing (translate, decompose and identify the logic to fulfill the intent), and 2) ensuring intent conformance (ongoing adaptation of the logic to ensure the intent is met, considering dynamic conditions). We use a 3-tier Large Language Model (LLM) pipeline to convert intents into Policy Trees, that are then executed using closed control loop automation. In this paper, we focus on assurance that is tasked with continuous monitoring, verification, and validation of the operational state, and corrective actions to ensure conformance with the target objectives. To do so, we use a generic LLM (OpenAI's GPT) with in-context learning and well-established decision-making algorithms (feedback controllers) to determine assurance actions and remediate intent deviation. We show that AI-driven policies can support intent fulfillment and assurance, and we discuss current limitations, benefits, and future directions to address critical challenges in using AI for network management, towards improved generalizability, scalability, and overall trustworthiness.
Paper
Full text
KPI Assurance and LLMs for Intent-Based Management
Semantic Scholar · Computer Science · 2025
Abstract
Intent-Based Management provides a shift in network management by automating the alignment of network operations with business objectives. However, primary challenges include: 1) intent processing (translate, decompose and identify the logic to fulfill the intent), and 2) ensuring intent conformance (ongoing adaptation of the logic to ensure the intent is met, considering dynamic conditions). We use a 3-tier Large Language Model (LLM) pipeline to convert intents into Policy Trees, that are then executed using closed control loop automation. In this paper, we focus on assurance that is tasked with continuous monitoring, verification, and validation of the operational state, and corrective actions to ensure conformance with the target objectives. To do so, we use a generic LLM (OpenAI's GPT) with in-context learning and well-established decision-making algorithms (feedback controllers) to determine assurance actions and remediate intent deviation. We show that AI-driven policies can support intent fulfillment and assurance, and we discuss current limitations, benefits, and future directions to address critical challenges in using AI for network management, towards improved generalizability, scalability, and overall trustworthiness.