AI 中文总结
研究在动态边缘网络中加速异构智能体协作的问题，提出PRADA框架，通过将PRM作为离线教师，结合轻量级策略和拉格朗日调度器解决资源竞争，大幅降低延迟并保留LLM准确性，还揭示阈值效应，为资源配置提供指导。
AI 中文摘要
在网络边缘部署大语言模型（LLMs）因成本高昂而受阻，但其推理质量不可或缺。边缘小模型与服务器LLM之间的异构协作是一个有前景的方向，但现有方法在多用户竞争、自回归生成和时变资源的动态条件下失效。本文提出了一种过程奖励模型（PRM）辅助的两阶段解耦加速（PRADA）框架，将PRM作为离线教师，其推理质量直觉被提炼为轻量级策略在本地筛选每一步，服务器的拉格朗日调度器通过阈值结构化策略解决资源竞争。在各种推理基准测试中，PRADA在大幅降低端到端延迟的同时，保留了LLM的绝大部分准确性。结果还揭示了服务器并行容量和总带宽的阈值效应，为联合配置计算和通信资源提供了可操作的指导。
英文摘要
Deploying large language models (LLMs) at the network edge is hindered by their enormous cost, yet the reasoning quality they provide remains indispensable. Heterogeneous collaboration between edge small models and a server LLM has emerged as a promising direction, but existing methods fail under the dynamic conditions of multi-user contention, autoregressive generation, and time-varying resources. This paper puts forward a process reward model (PRM)-aided two-stage decoupled acceleration (PRADA) framework, which is built on a fundamental change of perspective: instead of querying a PRM online, which cripples multi-user systems with prohibitive latency, we use the PRM solely as an offline teacher. Its reasoning-quality intuition is fully distilled into a lightweight policy that screen each step locally, without any context upload, while a Lagrangian scheduler at the server resolves resource contention through a threshold-structured policy. Across diverse reasoning benchmarks, PRADA retains the vast majority of the LLM's accuracy while substantially reducing end-to-end latency. The results further reveal threshold effects for both server parallel capacity and total bandwidth: performance saturates beyond critical resource levels, after which the system bottleneck shifts from queuing to computation or from communication to contention. These structural findings provide actionable guidance for joint provisioning of computation and communication resources without requiring per-benchmark tuning.
