Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2605.03788 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917462229909504 |
|---|---|
| author | Iannoli, Andrea Gigli, Lorenzo Sciullo, Luca Trotta, Angelo Di Felice, Marco |
| author_facet | Iannoli, Andrea Gigli, Lorenzo Sciullo, Luca Trotta, Angelo Di Felice, Marco |
| contents | Large Language Models (LLMs) are increasingly explored as high-level reasoning engines for cyber-physical systems, yet their application to real-time UAV swarm management remains challenging due to heterogeneous interfaces, limited grounding, and the need for long-running closed-loop execution. This paper presents a mission-agnostic, agent-enhanced LLM framework for UAV swarm control, where users express mission objectives in natural language and the system autonomously executes them through grounded, real-time interactions. The proposed architecture combines an LLM-based Agent Core with a Model Context Protocol (MCP) gateway and a Web-of-Drones abstraction based on W3C Web of Things (WoT) standards. By exposing drones, sensors, and services as standardized WoT Things, the framework enables structured tool-based interaction, continuous state observation, and safe actuation without relying on code generation. We evaluate the framework using ArduPilot-based simulation across four swarm missions and six state-of-the-art LLMs. Results show that, despite strong reasoning abilities, current general-purpose LLMs still struggle to achieve reliable execution - even for simple swarm tasks - when operating without explicit grounding and execution support. Task-specific planning tools and runtime guardrails substantially improve robustness, while token consumption alone is not indicative of execution quality or reliability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_03788 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Say the Mission, Execute the Swarm: Agent-Enhanced LLM Reasoning in the Web-of-Drones Iannoli, Andrea Gigli, Lorenzo Sciullo, Luca Trotta, Angelo Di Felice, Marco Artificial Intelligence Networking and Internet Architecture Robotics 68T42, 68T40, 68T05, 68M14, 93C85, 93C95 I.2.11; C.3; C.2.1; I.2.8; H.5.2 Large Language Models (LLMs) are increasingly explored as high-level reasoning engines for cyber-physical systems, yet their application to real-time UAV swarm management remains challenging due to heterogeneous interfaces, limited grounding, and the need for long-running closed-loop execution. This paper presents a mission-agnostic, agent-enhanced LLM framework for UAV swarm control, where users express mission objectives in natural language and the system autonomously executes them through grounded, real-time interactions. The proposed architecture combines an LLM-based Agent Core with a Model Context Protocol (MCP) gateway and a Web-of-Drones abstraction based on W3C Web of Things (WoT) standards. By exposing drones, sensors, and services as standardized WoT Things, the framework enables structured tool-based interaction, continuous state observation, and safe actuation without relying on code generation. We evaluate the framework using ArduPilot-based simulation across four swarm missions and six state-of-the-art LLMs. Results show that, despite strong reasoning abilities, current general-purpose LLMs still struggle to achieve reliable execution - even for simple swarm tasks - when operating without explicit grounding and execution support. Task-specific planning tools and runtime guardrails substantially improve robustness, while token consumption alone is not indicative of execution quality or reliability. |
| title | Say the Mission, Execute the Swarm: Agent-Enhanced LLM Reasoning in the Web-of-Drones |
| topic | Artificial Intelligence Networking and Internet Architecture Robotics 68T42, 68T40, 68T05, 68M14, 93C85, 93C95 I.2.11; C.3; C.2.1; I.2.8; H.5.2 |
| url | https://arxiv.org/abs/2605.03788 |