根据任务结构和使用频率智能淘汰缓存，显著降低多智能体系统延迟。
Workload-Aware Caching for Multi-Agent Systems
- 融合重计算成本、依赖节点数和调用频次构建评分函数
- 相比基线最高降64.7%延迟，平均降31.1%且接近无限缓存性能
- 适合优化多智能体系统中重复执行任务的效率瓶颈
多智能体系统将复杂任务分解为特定智能体执行的有向无环图（DAG），天然具备跨查询缓存中间结果的机会。然而，现有缓存淘汰策略仅依据访问历史统一处理所有缓存项，忽略了智能体执行环境中独有的结构与工作负载信号。本文提出一种工作负载感知的淘汰策略，综合重计算成本、DAG依赖节点数和智能体调用频率三个信号，构建统一评分函数，在内存受限下保留最具价值的缓存项。在三个涵盖不同复用模式的多智能体基准上评估，该策略相比未缓存基线最多降低64.7%延迟，平均比最优有限容量基线再降31.1%，逼近无界缓存性能，同时准确率优于或等于所有对比的有限容量方法。进一步表明，工作负载感知的内容缓存与其他优化方法（如计划级缓存、并行执行）具有互补性，各自针对多智能体流水线中的不同效率瓶颈。
原文摘要 · Abstract (English)
Multi-agent systems decompose complex tasks into directed acyclic graphs (DAGs) of specialized agent executions, creating natural opportunities for caching intermediate results across queries. However, existing cache eviction policies treat all cached entries uniformly based on access history, ignoring structural and workload signals uniquely available in agentic execution environments. We present a workload-aware eviction policy that combines three signals, namely recomputation cost, DAG dependency count, and agent invocation frequency, into a unified scoring function that retains the most valuable entries under memory constraints. Evaluated across three multi-agent benchmarks spanning diverse reuse regimes, our policy reduces latency by up to 64.7% relative to the uncached baseline and achieves on average a 31.1% latency reduction over the next best finite-capacity baseline, while approaching the performance of an unbounded cache and maintaining accuracy on par with or exceeding all competing finite-capacity methods. We further show that workload-aware content caching is complementary to other agentic system optimization methods, including plan-level caching and parallel agent execution, with each technique targeting a distinct efficiency bottleneck in multi-agent pipelines.
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。