Deadline-Driven Hierarchical Agentic Resource Sharing for AI Services and RAN Functions in AI-RAN
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914543516516352 |
|---|---|
| author | Li, Haiyuan Wu, Yulei Simeonidou, Dimitra |
| author_facet | Li, Haiyuan Wu, Yulei Simeonidou, Dimitra |
| contents | AI-RAN consolidates AI services and Radio Access Network (RAN) functions onto a unified, GPU-accelerated infrastructure at the network edge. However, compute sharing between real-time RAN functions and highly heterogeneous AI services requires coordination of scheduling decisions at mismatched timescales, and placement adaptation may require service migration across nodes with non-negligible interruptions. This paper proposes a hierarchical agentic framework (HAF) for compute sharing in AI-RAN that combines a large language model (LLM)-based agent for slow-timescale placement of AI services and RAN functions with a closed-form, deadline-aware convex algorithm for fast-timescale GPU/CPU allocation. The LLM agent is further equipped with a predictive critic that filters out migrations when the induced service interruption outweighs the expected service-level objective (SLO) benefit. Experimental results show that HAF reaches 90.0% overall SLO fulfillment, a 20.5% improvement over the strongest baseline, and raises AI service request fulfillment from 51% to 85.3%. Further evaluations show that HAF retains its advantage under diverse load conditions, while the critic consistently improves SLO fulfillment across multiple open-source LLM agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07547 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Deadline-Driven Hierarchical Agentic Resource Sharing for AI Services and RAN Functions in AI-RAN Li, Haiyuan Wu, Yulei Simeonidou, Dimitra Distributed, Parallel, and Cluster Computing Networking and Internet Architecture Systems and Control AI-RAN consolidates AI services and Radio Access Network (RAN) functions onto a unified, GPU-accelerated infrastructure at the network edge. However, compute sharing between real-time RAN functions and highly heterogeneous AI services requires coordination of scheduling decisions at mismatched timescales, and placement adaptation may require service migration across nodes with non-negligible interruptions. This paper proposes a hierarchical agentic framework (HAF) for compute sharing in AI-RAN that combines a large language model (LLM)-based agent for slow-timescale placement of AI services and RAN functions with a closed-form, deadline-aware convex algorithm for fast-timescale GPU/CPU allocation. The LLM agent is further equipped with a predictive critic that filters out migrations when the induced service interruption outweighs the expected service-level objective (SLO) benefit. Experimental results show that HAF reaches 90.0% overall SLO fulfillment, a 20.5% improvement over the strongest baseline, and raises AI service request fulfillment from 51% to 85.3%. Further evaluations show that HAF retains its advantage under diverse load conditions, while the critic consistently improves SLO fulfillment across multiple open-source LLM agents. |
| title | Deadline-Driven Hierarchical Agentic Resource Sharing for AI Services and RAN Functions in AI-RAN |
| topic | Distributed, Parallel, and Cluster Computing Networking and Internet Architecture Systems and Control |
| url | https://arxiv.org/abs/2605.07547 |