arXiv cs.AI· Yuquan Xiao, Qinghe Du, Chaoyang Zhang, Wenchi Cheng, Jingqing Wang, Tao Chen, Jiangzhou Wang·· 3 天前AI 评分18
队列感知 Token 通信：打通 AI 表征与无线服务
Queue-Aware Token Communications: Bridging AI Representation and Wireless Service
AI 导读
针对现有 Token 通信（TokenCom）研究假设 token 可即时传输、忽略 token 负载生成与无线服务能力时变之间失配所产生排队动态的问题，研究者提出 Queue-Aware TokenCom，将 token 队列显式纳入 AI 服务流程，并给出融合 AI 表征生成、token 负载管理、无线传输与下游任务推理的端到端架构。
正文 · 原文
Abstract:The rapid advancement of foundation models and edge intelligence is transforming wireless networks from data-oriented communication systems into artificial intelligence (AI)-native service platforms. Token communications (TokenCom) has emerged as a promising paradigm that directly transmits task-oriented AI representations. However, existing studies typically assume that generated tokens can be transmitted immediately, overlooking the queueing dynamics arising from the mismatch between token workload generation and time-varying wireless service capability. To address this limitation, we introduce Queue-Aware TokenCom, which explicitly incorporates token queues into the AI service pipeline. We present an end-to-end architecture integrating AI representation generation, token workload management, wireless transmission, and downstream task inference. We then discuss two key design directions: budget-aware token representation optimization and queue-aware token service optimization, with the token budget serving as a critical interface between AI performance and communication efficiency. Moreover, we investigate fixed and adaptive token budget strategies to characterize the fundamental tradeoff between AI performance and communication efficiency in dynamic wireless environments. Finally, we outline research directions toward closed-loop, task-aware, and scalable TokenCom systems.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.16730 [cs.AI] |
| (or arXiv:2610.16730v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16730 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuquan Xiao [view email]
[v1]
Mon, 12 Oct 2026 13:00:21 UTC (966 KB)
来源：arXiv cs.AI · arxiv.org