arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.03265cs.LGcs.AI
收藏

认知边缘计算:面向普适部署的大模型与AI智能体优化综述

Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment

Beijing Normal-Hong Kong Baptist University(北京师范大学-香港浸会大学联合国际学院);Institute of Artificial Intelligence and Future Networks, Beijing Normal University (Zhuhai)(北京师范大学(珠海)人工智能与未来网络研究院);The Hong Kong Polytechnic University(香港理工大学)

Xubin Wang, Qing Li, Weijia Jia

AI总结:

本文系统综述了认知边缘计算,提出涵盖模型优化、系统架构和自适应智能的统一框架,并给出标准化评估协议与实践指南,以在资源受限的边缘设备上高效、隐私保护地部署大语言模型和自主AI智能体。

摘要:

本文综述了认知边缘计算,将其视为在网络边缘资源受限设备上部署具备推理能力的大语言模型(LLMs)和自主AI智能体的一种实用且系统化的路径。我们提出了一个统一的、保持认知能力的框架,涵盖:(1)模型优化(量化、稀疏化、低秩适配、蒸馏),旨在在严格的内存/计算预算下保持多步推理能力;(2)系统架构(端侧推理、弹性卸载、云边协同),在延迟、能耗、隐私和容量之间进行权衡;(3)自适应智能(上下文压缩、动态路由、联邦个性化),根据任务难度和设备约束调整计算。我们综合了高效Transformer设计、多模态集成、硬件感知编译、隐私保护学习以及智能体工具使用等方面的进展,并将其映射到边缘特定的运行包络中。我们进一步提出了一个标准化评估协议,涵盖延迟、吞吐量、每token能耗、准确率、鲁棒性、隐私和可持续性,并给出明确的测量假设以增强可比性。剩余挑战包括模态感知推理基准、透明且可复现的能耗报告、面向边缘的安全/对齐评估以及多智能体测试平台。最后,我们给出了跨层协同设计算法、运行时和硬件的实践者指南,以在边缘设备上提供可靠、高效且隐私保护的认知能力。

英文摘要:

This article surveys Cognitive Edge Computing as a practical and methodical pathway for deploying reasoning-capable Large Language Models (LLMs) and autonomous AI agents on resource-constrained devices at the network edge. We present a unified, cognition-preserving framework spanning: (1) model optimization (quantization, sparsity, low-rank adaptation, distillation) aimed at retaining multi-step reasoning under tight memory/compute budgets; (2) system architecture (on-device inference, elastic offloading, cloud-edge collaboration) that trades off latency, energy, privacy, and capacity; and (3) adaptive intelligence (context compression, dynamic routing, federated personalization) that tailors computation to task difficulty and device constraints. We synthesize advances in efficient Transformer design, multimodal integration, hardware-aware compilation, privacy-preserving learning, and agentic tool use, and map them to edge-specific operating envelopes. We further outline a standardized evaluation protocol covering latency, throughput, energy per token, accuracy, robustness, privacy, and sustainability, with explicit measurement assumptions to enhance comparability. Remaining challenges include modality-aware reasoning benchmarks, transparent and reproducible energy reporting, edge-oriented safety/alignment evaluation, and multi-agent testbeds. We conclude with practitioner guidelines for cross-layer co-design of algorithms, runtime, and hardware to deliver reliable, efficient, and privacy-preserving cognitive capabilities on edge devices.

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。

↑