# TACOS: Task Agnostic COordinator of a multi-drone System

arXiv: https://arxiv.org/abs/2510.01869 · HTML: https://mlsanity.com/paper/2510.01869/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 2 Oct 2025.

## Builds on (most cited first, 13 of 13)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Building Cooperative Embodied Agents Modularly with Large Language Models](https://mlsanity.com/paper/2307.02485/) (2023)
- [RoCo: Dialectic Multi-Robot Collaboration with Large Language Models](https://mlsanity.com/paper/2307.04738/) (2023)
- [Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?](https://mlsanity.com/paper/2309.15943/) (2023)
- [UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility](https://mlsanity.com/paper/2501.02341/) (2025)
- [LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments](https://mlsanity.com/paper/2407.10031/) (2024)
- [MADER: Trajectory Planner in Multi-Agent and Dynamic Environments](https://mlsanity.com/paper/2010.11061/) (2020)
- [Multi-agent Motion Planning from Signal Temporal Logic Specifications](https://mlsanity.com/paper/2201.05247/) (2022)
- [SwarmGPT: Combining Large Language Models with Safe Motion Planning for Drone Swarm Choreography](https://mlsanity.com/paper/2412.08428/) (2024)
- [AuDeRe: Automated Strategy Decision and Realization in Robot Planning and Control via LLMs](https://mlsanity.com/paper/2504.03015/) (2025)
- [Designing Effective Human-Swarm Interaction Interfaces: Insights from a User Study on Task Performance](https://mlsanity.com/paper/2504.02250/) (2025)

## Built on by (most cited first, 2 of 2)

- [MultiUAV-Plat: An LLM-Oriented Platform, Benchmark and Framework for Multi-UAV Collaborative Task Planning](https://mlsanity.com/paper/2606.31073/) (2026)
- [Auto-HSI: Personalized human control of a robot swarm on demand by using LLMs for online automatic code generation](https://mlsanity.com/paper/2609.16346/) (2026)

## Abstract (arXiv)

When a single pilot is responsible for managing a multi-drone system, the task may demand varying levels of autonomy, from direct control of individual UAVs, to group-level coordination, to fully autonomous swarm behaviors for accomplishing high-level tasks. Enabling such flexible interaction requires a framework that supports multiple modes of shared autonomy. As language models continue to improve in reasoning and planning, they provide a natural foundation for such systems, reducing pilot workload by enabling high-level task delegation through intuitive, language-based interfaces. In this paper we present TACOS (Task-Agnostic COordinator of a multi-drone System), a unified framework that enables high-level natural language control of multi-UAV systems through Large Language Models (LLMs). TACOS integrates three key capabilities into a single architecture: a one-to-many natural language interface for intuitive user interaction, an intelligent coordinator for translating user intent into structured task plans, and an autonomous agent that executes plans interacting with the real world. TACOS allows a LLM to interact with a library of executable APIs, bridging semantic reasoning with real-time multi-robot coordination. We demonstrate the system on a real-world multi-drone system, and conduct an ablation study to assess the contribution of each module.