From Automated to Autonomous: Hierarchical Agent-native Network Architecture (HANA)
Quick Answer
The proposed Hierarchical Agent-native Network Architecture (HANA) enables Level 4/5 Autonomous Networks by integrating self-aware agents and a Dual-Driven Orchestrator, achieving an 86% reduction in Mean Time to Repair (MTTR) during congestion in a 5G Core environment.
Quick Take
The proposed Hierarchical Agent-native Network Architecture (HANA) enables Level 4/5 Autonomous Networks by integrating self-aware agents and a Dual-Driven Orchestrator, achieving an 86% reduction in Mean Time to Repair (MTTR) during congestion in a 5G Core environment.
Key Points
- HANA enables high-level autonomy through a reference architecture.
- The Dual-Driven Orchestrator coordinates specialized Executive Agents effectively.
- Agent self-awareness allows for strategic governance and fault recovery.
- Case studies confirm critical throughput sustainability under congestion.
- MTTR is reduced by 86%, enhancing operational resilience.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Comments: | This manuscript has been accepted by IEEE Networking Letters |
| Subjects: | Artificial Intelligence (cs.AI); Networking and Internet Architecture (cs.NI) |
| Cite as: | arXiv:2605.20608 [cs.AI] |
| (or arXiv:2605.20608v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.20608 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | B. Wu, S. Wang, Y. Liu, Y. -Q. Zhang, J. Sifakis and Y. Ouyang, "From Automated to Autonomous: Hierarchical Agent-native Network Architecture (HANA)," in IEEE Networking Letters, 2026 |
| Related DOI: | https://doi.org/10.1109/LNET.2026.3693226
DOI(s) linking to related resources |
Submission history
From: Binghan Wu [view email]
[v1]
Wed, 20 May 2026 01:50:12 UTC (280 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Procedural Memory Distillation: Online Reflection for Self-Improving Language Models
Procedural Memory Distillation (PMD) enhances reinforcement learning by converting cross-episode signals into reusable memory, improving Qwen3-8B and OLMo3-Instruct-7B models by 3.8-5.5% on SCIKNOWEVAL and 7.9-13.6% on . The co-evolution of policy and memory allows for more effective self-supervision, demonstrating significant performance gains when both components are active.