Guardado en:
Detalles Bibliográficos
Autores principales: Iannoli, Andrea, Gigli, Lorenzo, Sciullo, Luca, Trotta, Angelo, Di Felice, Marco
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