RALLY: Role-Adaptive LLM-Driven Yoked Navigation for Agentic UAV Swarms

TL;DR

This paper introduces RALLY, a novel framework combining LLM-driven semantic reasoning with adaptive role switching and semi-offline training to enhance UAV swarm navigation, coverage, and scalability.

Contribution

It proposes a role-adaptive, LLM-based navigation algorithm with a semantic decision framework, dynamic role heterogeneity, and a role-value mixing network for improved multi-UAV coordination.

Findings

Outperforms traditional methods in task coverage and convergence speed.

Demonstrates strong generalization in multi-UAV navigation tasks.

Effective semi-offline training of role strategies with RMIX.

Abstract

Intelligent control of Unmanned Aerial Vehicles (UAVs) swarms has emerged as a critical research focus, and it typically requires the swarm to navigate effectively while avoiding obstacles and achieving continuous coverage over multiple mission targets. Although traditional Multi-Agent Reinforcement Learning (MARL) approaches offer dynamic adaptability, they are hindered by the semantic gap in numerical communication and the rigidity of homogeneous role structures, resulting in poor generalization and limited task scalability. Recent advances in Large Language Model (LLM)-based control frameworks demonstrate strong semantic reasoning capabilities by leveraging extensive prior knowledge. However, due to the lack of online learning and over-reliance on static priors, these works often struggle with effective exploration, leading to reduced individual potential and overall system performance. To address these limitations, we propose a Role-Adaptive LLM-Driven Yoked navigation algorithm RALLY. Specifically, we first develop an LLM-driven semantic decision framework that uses structured natural language for efficient semantic communication and collaborative reasoning. Afterward, we introduce a dynamic role-heterogeneity mechanism for adaptive role switching and personalized decision-making. Furthermore, we propose a Role-value Mixing Network (RMIX)-based assignment strategy that integrates LLM offline priors with MARL online policies to enable semi-offline training of role selection strategies. Experiments in the Multi-Agent Particle Environment (MPE) environment and a Software-In-The-Loop (SITL) platform demonstrate that RALLY outperforms conventional approaches in terms of task coverage, convergence speed, and generalization, highlighting its strong potential for collaborative navigation in agentic multi-UAV systems.