面向智能体网络分布式管理的增强背压算法
Augmented Backpressure for Decentralized Management of Agentic Networks
浏览论文内容
中文总结 AI 辅助
该研究针对智能体基础模型服务网络的控制缺口，提出记忆增强背压（MABP）框架，通过联合建模队列与上下文记忆动态，扩大稳定区域并提供性能保证，实现分布式管理。
中文摘要 AI 辅助
智能体基础模型服务网络处理涵盖检索、规划、生成、验证及工具使用的请求。与传统通信网络不同，其控制性能依赖队列动态和上下文记忆状态，包括前缀/KV块、检索上下文、专家预热状态及已验证工具输出。这些状态源于执行历史，在有限本地预算下改变服务工作及下游后继规则。将其视为被动缓存或独立进程会导致排队控制缺口。为此，我们提出**记忆增强背压（MABP）**，这是针对有状态基础模型服务网络（SFMSNs）的队列-记忆控制框架，联合建模常规队列与因果上下文记忆动态。MABP按服务和状态类型表示每个请求，估计依赖记忆的工作量、惩罚及后继概率，每时隙读取队列和驻留记忆，通过依赖记忆的压力分数选择可行的路由、转移、激活及服务动作，并保留驻留对象与新生成对象的预算可行子集。我们证明了带条件紧性的占用测度容量外边界，显示建模上下文记忆可通过减少工作量和塑造转移严格扩大稳定区域，确立了感知记忆与忽略记忆决策的差异；还证明了精确帧-MABP的吞吐量和漂移加惩罚保证，以及近似求解器的有界损失扩展。
英文摘要
Agentic foundation-model service networks handle requests spanning retrieval, planning, generation, verification, and tool use. Unlike traditional communication networks, control performance depends on queue dynamics and contextual memory states, including prefix/KV blocks, retrieved contexts, expert warm states, and verified tool outputs. These states arise from execution history and alter service work and downstream successor laws under finite local budgets. Treating them as passive caches or an independent process leaves a queueing-control gap. To this end, we propose \emph{Memory-Augmented Backpressure} (MABP), a queue--memory control framework for stateful foundation-model service networks (SFMSNs) that jointly models commodity queues and causal contextual memory dynamics. MABP represents each request by service and state types, estimates memory-dependent work, penalties, and successor probabilities, then reads queues and resident memory each slot, selects feasible routing, transfer, activation, and service actions using a memory-dependent pressure score, and retains a budget-feasible subset of resident and newly generated objects. We prove an occupation-measure capacity outer bound with conditional tightness. We show that modeling contextual memory can strictly increase the stability region through work reduction and transition shaping, establishing a separation between memory-aware and memory-oblivious decisions. We also prove throughput and drift-plus-penalty guarantees for exact frame-MABP with bounded-loss extensions to approximate solvers.
