发表机构
Technical University of Catalonia (UPC); BrainOmega; i2CAT Foundation; Virginia Tech; Khalifa University of Science and Technology（加泰罗尼亚理工大学; BrainOmega; i2CAT基金会; 弗吉尼亚理工学院; 哈利法科学技术大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出目标导向语义通信（GOSC），通过闭环协同设计按消息价值调度发送，在搜索救援任务中以更少信道资源达成同等目标。
AI 中文摘要
由自主智能体（包括大语言模型（LLM）智能体）组成的团队必须在稀缺且不可靠的无线链路上进行协调。我们提出目标导向的语义通信（GOSC），这是一种闭环协同设计，根据每条消息对团队任务的价值，联合决定每个智能体发送什么、何时发送以及传输的可靠性。团队共同知识的边缘广播通过更新这些价值来闭合循环。我们证明，只有当消息的价值超过传递它的成本时才会发送消息，并且更有价值的消息获得更稳健的传输速率；我们还表明，只要无线预算未饱和，调度器就能精确解决每个调度步骤，这在95%的调度决策中成立。在未见场景上验证的搜索与救援任务中，GOSC以1.2至8.5倍更少的上行信道使用次数达到与精心调整的周期性语义方案相同的任务目标。在大多数设置中，这一优势在考虑实际数据包开销时仍然存在，当包含下行链路成本时，上行信道使用次数减少16.6倍，成本降低13.8倍；在救援任务中，当所有智能体共享一个上行链路时，这一优势也依然存在。粗略的价值估计就足够了，而忽略消息内容的价值可能会失败。使用三种不同的LLM，GOSC使用的信道次数减少3.2至3.5倍，而完成时间的改进取决于模型。
英文摘要
Teams of autonomous agents, including large language model (LLM) agents, must coordinate over scarce and unreliable wireless links. We propose goal-oriented semantic communication (GOSC), a closed-loop co-design that jointly decides what each agent sends, when it sends it, and how reliably it is transmitted, based on each message's value to the team task. An edge broadcast of the team's common knowledge closes the loop by updating these values. We prove that a message is sent only if its value exceeds the cost of delivering it and that more valuable messages receive more robust transmission rates, and we show that the scheduler solves each scheduling step exactly whenever the radio budget is not saturated, which held in 95% of scheduling decisions. In search-and-rescue missions validated on unseen scenarios, GOSC meets the same mission targets as carefully tuned periodic semantic schemes with 1.2--8.5 times fewer uplink channel uses. In most settings, this advantage persists with realistic packet overheads, reaching 16.6 times fewer uplink channel uses and 13.8 times lower cost when downlink costs are included; in the rescue task, it also persists when all agents share one uplink. Rough value estimates suffice, whereas values that ignore message content can fail. With three different LLMs, GOSC uses 3.2--3.5 times fewer channel uses, while completion-time gains depend on the model.
Comments13 pages, 5 figures, 13 Tables
