Managing Context and Communication in Distributed Agentic UAV Swarms

原文：Managing Context and Communication in Distributed Agentic UAV Swarms

作者：Andrea Iannoli, Ivan Zyrianoff, Angelo Trotta, Lorenzo Gigli, Marco Di Felice

来源：arXiv cs.RO（机器人）

正文

Computer Science > Multiagent Systems

arXiv:2610.01569v1 (cs)

[Submitted on 1 Oct 2026]

Title:Managing Context and Communication in Distributed Agentic UAV Swarms

Authors:Andrea Iannoli, Ivan Zyrianoff, Angelo Trotta, Lorenzo Gigli, Marco Di Felice

View a PDF of the paper titled Managing Context and Communication in Distributed Agentic UAV Swarms, by Andrea Iannoli and 4 other authors

View PDF

HTML (experimental)

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

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

多智能体 · 人工智能 · 机器学习 · cs.NI · 机器人

由「前沿雷达」于 2026-10-01 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。