From Automated to Autonomous: Hierarchical Agent-native Network Architecture (HANA)
The paper presents a new architecture called Hierarchical Agent-native Network Architecture (HANA) aimed at achieving higher levels of autonomy in networks. It emphasizes the transition from static automation to agent-native intelligence, addressing limitations in current operations. The proposed framework has been validated in a 5G Core environment, demonstrating significant improvements in operational resilience and efficiency.
- ▪The architecture enables high-level autonomy through a hierarchical multi-agent reference model.
- ▪A Dual-Driven Orchestrator coordinates specialized Executive Agents and utilizes a shared Public Memory.
- ▪The integration of agent self-awareness allows for better strategic governance and fault recovery.
- ▪Case studies show an 86% reduction in Mean Time to Repair (MTTR) under congestion.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.20608 (cs) [Submitted on 20 May 2026] Title:From Automated to Autonomous: Hierarchical Agent-native Network Architecture (HANA) Authors:Binghan Wu, Shoufeng Wang, Yunxin Liu, Ya-Qin Zhang, Joseph Sifakis, Ye Ouyang View a PDF of the paper titled From Automated to Autonomous: Hierarchical Agent-native Network Architecture (HANA), by Binghan Wu and 5 other authors View PDF HTML (experimental) 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.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
