From Intents to Actions: Agentic AI in Autonomous Networks

2026-02-01

AI Summary

This work addresses the challenge of automatically translating diverse and often conflicting high-level service intents in telecommunications networks—such as ultra-low latency, high throughput, and energy efficiency—into low-level control actions. The paper proposes the first multi-agent system that integrates large language models, multi-objective optimization, and multi-objective reinforcement learning. In this framework, a supervised interpreter parses and refines natural language intents; an optimizer formulates them into tractable optimization problems and analyzes trade-offs among objectives; and a controller executes actions along the Pareto frontier according to specified preferences, thereby establishing an end-to-end closed-loop mapping from intent to control. The system supports dynamic adaptation and scalability, efficiently approximating the optimal performance boundary under complex constraints and significantly enhancing network autonomy and intent fulfillment.

Technology Category

• Multiagent Systems: Agent Communication
• Planning, Routing, and Scheduling: Planning with Language Models
• Intelligent Robots: Multi-Robot Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Telecommunication networks are increasingly expected to operate autonomously while supporting heterogeneous services with diverse and often conflicting intents -- that is, performance objectives, constraints, and requirements specific to each service. However, transforming high-level intents -- such as ultra-low latency, high throughput, or energy efficiency -- into concrete control actions (i.e., low-level actuator commands) remains beyond the capability of existing heuristic approaches. This work introduces an Agentic AI system for intent-driven autonomous networks, structured around three specialized agents. A supervisory interpreter agent, powered by language models, performs both lexical parsing of intents into executable optimization templates and cognitive refinement based on feedback, constraint feasibility, and evolving network conditions. An optimizer agent converts these templates into tractable optimization problems, analyzes trade-offs, and derives preferences across objectives. Lastly, a preference-driven controller agent, based on multi-objective reinforcement learning, leverages these preferences to operate near the Pareto frontier of network performance that best satisfies the original intent. Collectively, these agents enable networks to autonomously interpret, reason over, adapt to, and act upon diverse intents and network conditions in a scalable manner.

Problem

• intent-driven networking
• autonomous networks
• service intents
• control actions
• network autonomy

Innovation

• Agentic AI
• intent-driven networking
• multi-objective reinforcement learning
• Pareto optimization
• autonomous networks