针对工业流程查询延迟问题，提出时间语义缓存与工作流优化方案。
Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines
- 引入时间语义缓存和依赖感知并行执行，降低重复计算开销。
- 工作流优化使端到端延迟降低40.0%，速度提升1.67倍。
- 揭示参数丰富查询中纯语义缓存的失效风险，适合工业AI系统开发者。
工业资产操作流程对延迟敏感，单个用户查询需协调传感器数据、工单、故障模式、预测工具及领域专用代理。我们在AssetOpsBench（AOB）上评估该问题，其计划-执行管道存在工具发现、大模型规划、MCP工具执行和最终摘要等重复开销。现有大模型缓存技术如KV缓存复用和基于嵌入的语义缓存专为聊天服务设计，在输出有效性依赖时间、设备或传感器参数时失效。我们提出两个互补优化层：时间语义缓存与结合磁盘缓存工具发现和依赖感知并行执行的工作流优化。工作流优化带来1.67倍加速，中位端到端延迟降低约40.0%；时间缓存在命中时实现中位30.6倍加速。结果还揭示了纯语义缓存在参数密集型工业查询中的失效模式，为基于MCP的代理基准评估中的缓存选择与评估正确性关系提供了关键分析。
原文摘要 · Abstract (English)
Industrial asset operations workflows are latency-sensitive because a single user query may require coordination over sensor data, work orders, failure modes, forecasting tools, and domain-specific agents. We evaluate this problem on AssetOpsBench (AOB), an industrial agent benchmark whose plan-execute pipeline exposes repeated overhead from tool discovery, LLM planning, MCP tool execution, and final summarization. Existing LLM caching techniques such as KV-cache reuse and embedding-based semantic caching were designed for chatbot serving and break down when output validity depends on time, asset, or sensor parameters. We propose two complementary optimization layers for AOB plan-execute pipelines: a temporal semantic cache and a set of MCP workflow optimizations combining disk-backed tool-discovery caching and dependency-aware parallel step execution. MCP workflow optimizations corresponded to a 1.67x speedup and reduced median end-to-end latency by about 40.0% while the temporal-cache benchmark achieved a median of 30.6x speedup on cache hits. Beyond the speedup, our results expose a concrete failure mode of pure semantic caching for parameter-rich industrial queries, providing a critical analysis of how caching choices interact with evaluation correctness in MCP-backed agent benchmarks.
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。