Talk Less, Fly Lighter: Autonomous Semantic Compression for UAV Swarm Communication via LLMs

2025-08-16

AI Summary

High-frequency inter-UAV communication under bandwidth constraints leads to semantic communication inefficiency in drone swarms. Method: This paper proposes the first large language model (LLM)-driven autonomous semantic compression framework tailored for UAV coordination. It introduces a unified communication-execution pipeline that jointly incorporates system prompts and task instructions to enable end-to-end semantic encoding and decoding. Extensive evaluations are conducted in a 2D simulation environment, assessing the adaptability and stability of nine state-of-the-art LLMs across multi-hop topologies, varying environmental complexity, and scalable swarm sizes. Results/Contribution: The framework preserves critical task semantics while achieving an average communication load reduction of 62.3%. It empirically demonstrates, for the first time, the feasibility and robustness of deploying lightweight LLMs for semantic communication in bandwidth-constrained UAV edge networks—establishing a novel paradigm for semantic-level collaboration among resource-constrained intelligent edge agents.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Agent Communication

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The rapid adoption of Large Language Models (LLMs) in unmanned systems has significantly enhanced the semantic understanding and autonomous task execution capabilities of Unmanned Aerial Vehicle (UAV) swarms. However, limited communication bandwidth and the need for high-frequency interactions pose severe challenges to semantic information transmission within the swarm. This paper explores the feasibility of LLM-driven UAV swarms for autonomous semantic compression communication, aiming to reduce communication load while preserving critical task semantics. To this end, we construct four types of 2D simulation scenarios with different levels of environmental complexity and design a communication-execution pipeline that integrates system prompts with task instruction prompts. On this basis, we systematically evaluate the semantic compression performance of nine mainstream LLMs in different scenarios and analyze their adaptability and stability through ablation studies on environmental complexity and swarm size. Experimental results demonstrate that LLM-based UAV swarms have the potential to achieve efficient collaborative communication under bandwidth-constrained and multi-hop link conditions.

Problem

• Enhancing UAV swarm communication via LLM-driven semantic compression
• Reducing bandwidth load while preserving critical task semantics
• Evaluating LLM adaptability in diverse environmental scenarios

Innovation

• LLM-driven autonomous semantic compression for UAVs
• Simulation scenarios with varying complexity levels
• Integration of system and task instruction prompts