AeroWeaver: An Embodied-Agent Harness for Weaving Aerial Skills into Distributed, Adaptive Swarm Execution

2026-09-16

AI Summary

AeroWeaver通过连接语义决策与控制技能、组织角色条件本地代理进行分布式协调及利用奖励引导在线更新，解决了将大型语言模型应用于无人机群时面临的执行能力、任务推理与分布执行、持续适应性问题。

Abstract

Collective intelligence is a collaborative autonomy paradigm in which multiple agents pursue shared objectives through local perception, information exchange, and coordinated action. UAV swarms embody this paradigm by coordinating multiple vehicles in tasks such as search, inspection, and tracking. Recent advances in large language model (LLM) agents have strengthened natural-language task understanding and high-level planning, providing a flexible semantic interface between mission descriptions and collective behavior. While these advances expand semantic reasoning, applying LLM agents to UAV swarms raises challenges in grounding model decisions in executable capabilities, reconciling global task reasoning with distributed execution, and using mission-specific experience for continual adaptation. To address these challenges, we introduce AeroWeaver, an embodied-agent harness that weaves individual UAV skills into coordinated mission-level behavior. AeroWeaver connects semantic decisions to governed skills, organizes role-conditioned local agents for distributed coordination, and uses role-indexed state-action-reward experience to refine skill selection online. Experiments and runtime validation show that AeroWeaver maintains valid skill execution under tested conditions and supports body-local multi-UAV operation without a central agent generating joint actions from global context, while reward-guided online updates provide a training-free path for adaptive learning swarm agents from accumulated execution experience. Code: https://github.com/Admire-ljb/AeroWeaver.

Problem

• UAV swarms
• large language model agents
• semantic reasoning
• distributed coordination
• adaptive learning

Innovation

• Embodied-Agent Harness
• Distributed Coordination
• Online Adaptation
• Role-Conditioned Agents
• Reward-Guided Learning