From Intents to Actions: Agentic AI in Autonomous Networks

ICLR 2026 Conference Submission18506 Authors

Keywords: Agentic AI, Online Bayesian Optimization, Multi-Objective Reinforcement Learning, Autonomous Networks, Telecommunication

TL;DR: We propose an Agentic AI system that interprets service intents, optimizes trade-offs, and controls networks with multi-objective reinforcement learning to achieve autonomous, intent-driven performance.

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, translating 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. An interpreter agent, powered by a large language model, parses network intents, decomposes them into sub-intents, and generates executable optimization templates. An optimizer agent converts these templates into tractable optimization problems, analyzes trade-offs, and derives preferences across objectives. Lastly, a preference-driven controller, based on multi-objective reinforcement learning, leverages these preferences to operate near the Pareto front of network performance that best satisfies the original intent. Collectively, these agents enable networks to autonomously interpret, reason over, and act upon diverse intents in a scalable and adaptive manner.

Primary Area: other topics in machine learning (i.e., none of the above)

Submission Number: 18506