解决100+智能体边缘计算中性能超线性下降问题，提升系统可扩展性。
A Delta-Aware Orchestration Framework for Scalable Multi-Agent Edge Computing
- 通过差分神经缓存、优先级动作空间剪枝与硬件亲和性匹配，协同优化多智能体系统。
- 在200个智能体部署下，延迟降低62%（280ms vs 735ms），实现近线性增长。
- 适合大规模城市智能监控等需要高并发边缘计算的场景。
当智能体数量超过100时，会出现协同崩溃现象，导致性能呈超线性恶化，现有优化方法无法缓解。我们在智慧城市部署中使用MADDPG测试150个摄像头，发现截止时间满足率从78%降至34%，年成本超支约18万美元。以往研究仅孤立解决三个根源问题：动作空间指数增长、相邻智能体计算冗余、任务无关的硬件调度。本文提出DAOEF（Delta-Aware Orchestration for Edge Federations）框架，同时应对三者：(1) 差分神经缓存通过存储中间层激活并仅计算输入差异，在保持2%精度损失的前提下，命中率提升至72%（对比输出级缓存35%）；(2) 基于重要性的动作空间剪枝将协调复杂度从O(n²)降至O(n log n)，优化损失低于6%；(3) 学习式硬件亲和性匹配，将任务分配至最优加速器（GPU/CPU/NPU/FPGA），避免叠加失配惩罚。隔离实验表明，任一机制缺失均使延迟增加超40%，证明其协同必要性。在四个数据集（100–250智能体）及20设备物理测试平台中，联合应用三大机制带来1.45倍乘法增益。200智能体云端部署中，延迟减少62%（280毫秒对735毫秒），且在250智能体内实现亚线性增长。
原文摘要 · Abstract (English)
The Synergistic Collapse occurs when scaling beyond 100 agents causes superlinear performance degradation that individual optimizations cannot prevent. We observe this collapse with 150 cameras in Smart City deployment using MADDPG, where Deadline Satisfaction drops from 78% to 34%, producing approximately $180,000 in annual cost overruns. Prior work has addressed each contributing factor in isolation: exponential action-space growth, computational redundancy among spatially adjacent agents, and task-agnostic hardware scheduling. None has examined how these three factors interact and amplify each other. We present DAOEF (Delta-Aware Orchestration for Edge Federations), a framework that addresses all three simultaneously through: (1) Differential Neural Caching, which stores intermediate layer activations and computes only the input deltas, achieving 2.1x higher hit ratios (72% vs. 35%) than output-level caching while staying within 2% accuracy loss through empirically calibrated similarity thresholds; (2) Criticality-Based Action Space Pruning, which organizes agents into priority tiers and reduces coordination complexity from O(n2) to O(n log n) with less than 6% optimality loss; and (3) Learned Hardware Affinity Matching, which assigns tasks to their optimal accelerator (GPU, CPU, NPU, or FPGA) to prevent compounding mismatch penalties. Controlled factor-isolation experiments confirm that each mechanism is necessary but insufficient on its own: removing any single mechanism increases latency by more than 40%, validating that the gains are interdependent rather than additive. Across four datasets (100-250 agents) and a 20-device physical testbed, DAOEF achieves a 1.45x multiplicative gain over applying the three mechanisms independently. A 200-agent cloud deployment yields 62% latency reduction (280 ms vs. 735 ms), sub-linear latency growth up to 250 agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。