arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.07321eess.SP
收藏

无线上下文工程用于高效的移动群体AI和边缘通用智能

Wireless Context Engineering for Efficient Mobile Agentic AI and Edge General Intelligence

Nanyang Technological University（南洋理工大学）；Xidian University（西安电子科技大学）；University of Sydney（悉尼大学）；Tohoku University（东北大学）；Sungkyunkwan University（成均馆大学）

Changyuan Zhao, Jiacheng Wang, Yunting Xu, Zan Li, Abbas Jamalipour, Dong In Kim

备注：
8 pages, 4 figures
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出无线上下文工程，通过优化无线边缘智能的上下文管理，提升移动群体AI和边缘通用智能的效率。

摘要：

未来无线网络需要越来越强大的智能来支持传感、通信和自主决策。尽管扩展定律表明通过扩大模型容量来提高性能，但实际的边缘部署从根本上受到延迟、能量和内存的限制，使无限制的模型扩展不可行。这创造了迫切需求，即通过过滤冗余观察并聚焦于高影响数据来最大化有限推理时间输入的效用。在大型语言模型和生成式人工智能中，上下文工程已作为一种关键范式，通过选择性地结构化和注入任务相关的信息来指导推理。受这一成功启发，我们将上下文工程扩展到无线系统，提供一种系统的方法来增强边缘AI性能，而无需增加模型复杂性。在动态环境中，例如，波束预测可以从增强即时信道测量与上下文线索如用户移动趋势或环境感知的传播先验相结合。我们正式引入无线上下文工程，并提出无线上下文通信框架（WCCF）以适应性地协调无线上下文在推理时间限制下。本工作为研究人员提供了基础视角和实用设计维度，以管理无线边缘智能的无线上下文。一个启用了ISAC的波束预测案例研究展示了所提出范式在受限传感预算下的有效性。

英文摘要：

Future wireless networks demand increasingly powerful intelligence to support sensing, communication, and autonomous decision-making. While scaling laws suggest improving performance by enlarging model capacity, practical edge deployments are fundamentally constrained by latency, energy, and memory, making unlimited model scaling infeasible. This creates a critical need to maximize the utility of limited inference-time inputs by filtering redundant observations and focusing on high-impact data. In large language models and generative artificial intelligence (AI), context engineering has emerged as a key paradigm to guide inference by selectively structuring and injecting task-relevant information. Inspired by this success, we extend context engineering to wireless systems, providing a systematic way to enhance edge AI performance without increasing model complexity. In dynamic environments, for example, beam prediction can benefit from augmenting instantaneous channel measurements with contextual cues such as user mobility trends or environment-aware propagation priors. We formally introduce wireless context engineering and propose a Wireless Context Communication Framework (WCCF) to adaptively orchestrate wireless context under inference-time constraints. This work provides researchers with a foundational perspective and practical design dimensions to manage the wireless context of wireless edge intelligence. An ISAC-enabled beam prediction case study illustrates the effectiveness of the proposed paradigm under constrained sensing budgets.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑