Aerial Agentic AI: Synergizing LLM and SLM for Low-Altitude Wireless Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915886614446080 |
|---|---|
| author | Dong, Li Jiang, Feibo Wang, Kezhi Pan, Cunhua Kim, Dong In Hossain, Ekram |
| author_facet | Dong, Li Jiang, Feibo Wang, Kezhi Pan, Cunhua Kim, Dong In Hossain, Ekram |
| contents | Low-Altitude Wireless Networks (LAWNs), composed of Unmanned Aerial Vehicles (UAVs) and mobile terminals, are emerging as a critical extension of 6G. However, applying Large Language Models in LAWNs faces three major challenges: 1) Computational and energy constraints; 2) Communication and bandwidth limitations; 3) Real-time and reliability conflicts. To address these challenges, we propose Aerial Agentic AI, a hierarchical framework integrating UAV-side fast-thinking Small Language Model (SLMs) with BS-side slow-thinking Large Language Model (LLMs). First, we design SLM-based Agents capable of on-board perception, short-term memory enhancement, and real-time decision-making on the UAVs. Second, we implement a LLM-based Agent system that leverages long-term memory, global knowledge, and tool orchestration at the Base Station (BS) to perform deep reasoning, knowledge updates, and strategy optimization. Third, we establish an efficient hierarchical coordination mechanism, enabling UAVs to execute high-frequency tasks locally while synchronizing with the BS only when necessary. Experimental results validate the effectiveness of the proposed Aerial Agentic AI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_22866 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Aerial Agentic AI: Synergizing LLM and SLM for Low-Altitude Wireless Networks Dong, Li Jiang, Feibo Wang, Kezhi Pan, Cunhua Kim, Dong In Hossain, Ekram Information Theory Low-Altitude Wireless Networks (LAWNs), composed of Unmanned Aerial Vehicles (UAVs) and mobile terminals, are emerging as a critical extension of 6G. However, applying Large Language Models in LAWNs faces three major challenges: 1) Computational and energy constraints; 2) Communication and bandwidth limitations; 3) Real-time and reliability conflicts. To address these challenges, we propose Aerial Agentic AI, a hierarchical framework integrating UAV-side fast-thinking Small Language Model (SLMs) with BS-side slow-thinking Large Language Model (LLMs). First, we design SLM-based Agents capable of on-board perception, short-term memory enhancement, and real-time decision-making on the UAVs. Second, we implement a LLM-based Agent system that leverages long-term memory, global knowledge, and tool orchestration at the Base Station (BS) to perform deep reasoning, knowledge updates, and strategy optimization. Third, we establish an efficient hierarchical coordination mechanism, enabling UAVs to execute high-frequency tasks locally while synchronizing with the BS only when necessary. Experimental results validate the effectiveness of the proposed Aerial Agentic AI. |
| title | Aerial Agentic AI: Synergizing LLM and SLM for Low-Altitude Wireless Networks |
| topic | Information Theory |
| url | https://arxiv.org/abs/2603.22866 |