用大模型辅助谈判，让边缘计算任务调度更智能高效。
Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing
- 用大模型生成语义化请求，逐步披露上下文并多轮修改方案。
- 降低3%延迟违规，20个代理时冲突解决率达91%，效率提升22%。
- 适合需要智能协商的边缘计算场景，尤其面对不确定环境。
流处理系统越来越多地运行在异构的移动边缘-云基础设施上，工作负载波动、资源竞争和严格的QoS要求使得去中心化调度变得复杂。本文提出MAS-DecStream，其核心是LLM-MR-CNP：在经典合同网协议基础上，引入语义化CSP表述、渐进式上下文披露、多轮提案修订、谈判记忆和确定性验证。边缘集群代理基于本地观测、预测资源状态和定性运行时上下文，优化自然语言形式的任务卸载建议，而硬性资源与QoS约束保持确定性。基于阿里巴巴ASI Trace的实验在三个层面评估该方法：单轮与多轮CNP对比、规则基与大模型辅助优化对比、固定模型单轮与多轮协商对比。在所评估配置下，MAS-DecStream将延迟违规降至3%，消除资源超分配，20个代理时冲突解决率达到0.91，效用相比多轮规则基基线最高提升22%。另一次25组案例评估显示模型与提示依赖的精度-成本权衡。结果表明，多轮协议优化是主要增益来源，大模型在定性与不确定性运行时上下文中更具价值。
原文摘要 · Abstract (English)
Stream-processing systems increasingly operate across heterogeneous mobile edge--cloud infrastructures, where workload volatility, resource contention, and stringent quality-of-service (QoS) requirements complicate decentralized scheduling. This paper proposes \emph{MAS-DecStream}, whose main contribution is \emph{LLM-MR-CNP}: an extension of the classical Contract Net Protocol with semantic CFP formulation, progressive context disclosure, multi-round proposal revision, negotiation memory, and deterministic validation. Edge-cluster agents refine natural-language offloading proposals from local observations, predicted resource states, and qualitative runtime context, while hard resource and QoS constraints remain deterministic. Experiments derived from the Alibaba ASI Trace evaluate the extension at three levels: single- versus multi-round CNP, rule-based versus LLM-assisted refinement, and fixed-model single- versus multi-round negotiation. Under the evaluated configurations, MAS-DecStream reduces latency violations to 3\%, eliminates resource overcommitment, reaches a conflict-resolution rate of 0.91 with 20 agents, and improves utility by up to 22\% over the multi-round rule-based baseline. A separate 25-case evaluation shows model- and prompt-dependent accuracy--cost trade-offs. The results provide initial evidence that multi-round CNP refinement is the principal protocol-level gain, with LLM assistance adding value for qualitative and uncertain runtime context.
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。