LLM辅助多轮合同网协议用于移动边缘计算流处理调度
原标题：Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing
AI 摘要
本文提出 MAS-DecStream 系统，其核心是 LLM-MR-CNP 协议，扩展了经典合同网协议，引入语义化 CFP 生成、渐进式上下文披露、多轮提案修订、协商记忆和确定性验证。实验基于阿里 ASI 追踪数据，结果显示该方案将延迟违规率降至 3%，消除资源过度承诺，在 20 个代理下冲突解决率达 0.91，效用相比多轮规则基线提升最多 22%。研究表明多轮 CNP 细化是协议层面的主要收益，LLM 辅助在定性和不确定运行时上下文中增加价值。
正文节选
Multi-Agent Scheduling with LLM-Assisted Contract Net Negotiation for Stream Processing in Mobile Edge Computing Abstract 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 MAS-DecStream, whose main contribution is LLM-MR-CNP: an extension of the classical Contract Net Protocol with semanti