# Say the Mission, Execute the Swarm: Agent-Enhanced LLM Reasoning in the Web-of-Drones

arXiv: https://arxiv.org/abs/2605.03788 · HTML: https://mlsanity.com/paper/2605.03788/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 5 May 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 10 of 10)

- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [ChatGPT for Robotics: Design Principles and Model Abilities](https://mlsanity.com/paper/2306.17582/) (2023)
- [SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models](https://mlsanity.com/paper/2309.10062/) (2023)
- [UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility](https://mlsanity.com/paper/2501.02341/) (2025)
- [Swarm-GPT: Combining Large Language Models with Safe Motion Planning for Robot Choreography Design](https://mlsanity.com/paper/2312.01059/) (2023)
- [FlockGPT: Guiding UAV Flocking with Linguistic Orchestration](https://mlsanity.com/paper/2405.05872/) (2024)
- [LLM-DaaS: LLM-driven Drone-as-a-Service Operations from Text User Requests](https://mlsanity.com/paper/2412.11672/) (2024)
- [GSCE: A Prompt Framework with Enhanced Reasoning for Reliable LLM-driven Drone Control](https://mlsanity.com/paper/2502.12531/) (2025)
- [LLM-Powered Swarms: A New Frontier or a Conceptual Stretch?](https://mlsanity.com/paper/2506.14496/) (2025)
- [Talk Less, Fly Lighter: Autonomous Semantic Compression for UAV Swarm Communication via LLMs](https://mlsanity.com/paper/2508.12043/) (2025)

## Built on by (most cited first, 4 of 4)

- [MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning](https://mlsanity.com/paper/2606.31073/) (2026)
- [Device Context Protocol: A Compact, Safety-First Architecture for LLM-Driven Control of Constrained Devices](https://mlsanity.com/paper/2605.26159/) (2026)
- [AeroWeaver: An Embodied-Agent Harness for Weaving Aerial Skills into Distributed, Adaptive Swarm Execution](https://mlsanity.com/paper/2609.18520/) (2026)
- [Managing Context and Communication in Distributed Agentic UAV Swarms](https://mlsanity.com/paper/2610.01569/) (2026)

## Abstract (arXiv)

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.