arXiv：cs.LG（机器学习，全量分类）· Andrea Iannoli, Ivan Zyrianoff, Angelo Trotta, Lorenzo Gigli, Marco Di Felice·· 15 小时前AI 评分37
分布式智能体无人机集群如何管理上下文与通信
Managing Context and Communication in Distributed Agentic UAV Swarms
AI 导读
研究提出一种分布式无人机智能体架构，每架无人机搭载独立 SLM，通过事件驱动的 reason-act-observe 生命周期实现持续本地控制，运行时知识以结构化原子笔记形式分为 core、local 和 peer-specific 记忆，并由确定性兴趣感知 gossip 引擎按语义新颖度和时效性选择性传播。
正文
Abstract:Unmanned aerial vehicle (UAV) swarms increasingly rely on language-model agents to provide adaptive mission-level reasoning in uncertain environments. Fully distributed control, in which each UAV hosts an independent Small Language Model (SLM), removes reliance on a centralized coordinator but introduces an information-management problem: long-running interaction histories can degrade the reasoning context, while indiscriminate information dissemination increases communication and inference overhead. We address these challenges with a distributed UAV-agent architecture that enables continuous local SLM control through an event-driven reason-act-observe lifecycle. Runtime knowledge is represented as structured atomic notes and organized into core, local, and peer-specific memory. A deterministic interest-aware gossip engine selectively disseminates these notes according to recipient-specific semantic novelty and recency. We evaluate the architecture using ten UAVs in a simulated search-and-rescue mission. Our approach completes all experimental runs, whereas unrestricted flooding messages completes only 70-85\%, and delegating forwarding decisions to the SLM prevents mission completion in every run. Compared with unrestricted flooding, our approach approximately halves inference-token consumption, reduces transmitted data, and achieves lower survivor-count error.
| Comments: | 12 pages, 4 figures. This paper has been accepted for presentation at the 24th IEEE Consumer Communications & Networking Conference 2027 (CCNC 2027) |
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI); Robotics (cs.RO) |
| MSC classes: | 68T42, 68T40, 68T05, 68M14, 93C85, 93C95 |
| ACM classes: | I.2.11; C.3; C.2.1; I.2.8; H.5.2 |
| Cite as: | arXiv:2610.01569 [cs.MA] |
| (or arXiv:2610.01569v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.01569 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Andrea Iannoli [view email]
[v1]
Thu, 1 Oct 2026 12:30:29 UTC (610 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org