cs.AIOct 12, 2026

Queue-Aware Token Communications: Bridging AI Representation and Wireless Service

Authors: Yuquan Xiao, Qinghe Du, Chaoyang Zhang, Wenchi Cheng, Jingqing Wang, Tao Chen, Jiangzhou Wang

Organizations: School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an 710049, China. · State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an 710071, China. · VTT Technical Research Centre of Finland, 02140 Espoo, Finland. · National Mobile Communications Research Laboratory, Southeast University, Nanjing 210096, China.

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

Fig. 1: End-to-end architecture of Queue-aware TokenCom. Task-relevant tokens are compressed into a workload, queued, and served over a time-varying wireless channel. The queue-control policy adapts token and wireless decisions according to the queue and channel states, balancing task-level performance with queue-level service.
Fig. 2: Budget-aware model training. The AI model should be trained by sampling budget values based on the token budget distribution.
Fig. 3: Task-indexed queueing process. Due to the adaptive token budget control, the amount of data to be transmitted varies across tasks. The commonly-used time-indexed queueing process might be challenging to directly characterize the task-level communication delay.
Fig. 4: An image classification scenario, where the adaptive Top- KK token selection module selects the most informative tokens under a give token budget, and the selected are delivered to the receiver for subsequent inference.
Fig. 5: Token budget distributions and per-budget classification accuracy under different values of the control parameter α\alpha . The results show that changes in the training budget distribution lead to a redistribution of performance across the shared token-budget configurations.
More in this topic

Wireless Communications

Wireless communications studies how information is sent over radio links and how networks manage signals, spectrum, and resources reliably.

See all 400 papers

Explore similar work

CardsList

  1. Explainable Task-Oriented Token Communication for AI-Native 6G Networks

    Jun 12, 2026Feibo Jiang, Lei Mao, Li Dong +36G NetworksVisual Tokenization

  2. TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems

    May 20, 2026Sige Liu, Kezhi WangUnequal Error ProtectionSemantic Communication

    Department of Computer Science, Brunel University London, Uxbridge UB8 3PH, U.K.

  3. Context-Aware Wireless Token Communication via Joint Token Masking and Detection

    May 4, 2026Junyong Shin, Joohyuk Park, Yongjeong Oh +3

    Department of Electrical Engineering, POSTECH, Pohang, Gyeongbuk 37673, Republic of Korea · Information Systems Technology and Design Pillar, Singapore University of Technology and Design, Singapore 487372 · School of Electrical and Mechanical Engineering, The University of Adelaide, SA 5005, Australia