From Automated to Autonomous: Hierarchical Agent-native Network Architecture (HANA)

2026-05-19

AI Summary

Current network operations rely heavily on static scripts and lack the cognitive capabilities necessary to handle anomalies, thereby hindering the realization of Level 4/5 network autonomy. This work proposes a hierarchical, multi-agent native architecture featuring a dual-driven orchestrator that coordinates specialized execution agents. By introducing a shared public memory for unified domain knowledge management and integrating agent self-awareness mechanisms, the system uniquely combines deliberate strategic planning with reflexive fault recovery within autonomous networks. Evaluated in a 5G core network environment, the proposed approach maintains critical throughput under congestion and reduces mean time to repair (MTTR) by 86%.

Abstract

Realizing Level 4/5 Autonomous Networks (AN) demands a shift from static automation to agent-native intelligence. Current operations, reliant on rigid scripts, lack the cognitive agency to handle off-nominal conditions. To address this, this letter proposes a hierarchical multi-agent reference architecture enabling high-level autonomy. The framework features a Dual-Driven Orchestrator that coordinates specialized Executive Agents, supported by a shared Public Memory for unified domain knowledge. A key innovation is the integration of agent self-awareness, which empowers the system to harmonize deliberative strategic governance with reflexive fault recovery. We instantiate and validate this architecture within a 5G Core environment. Case studies demonstrate that the system sustains critical throughput under congestion and reduces Mean Time to Repair (MTTR) by 86%, confirming its efficacy in unifying strategic planning with operational resilience.

Problem

• Autonomous Networks
• Cognitive Agency
• Off-nominal Conditions
• Network Automation
• Self-awareness

Innovation

• agent-native
• hierarchical multi-agent architecture
• self-awareness
• autonomous networks
• Dual-Driven Orchestrator