评估代理型规划执行流水线中的时间语义缓存与工作流优化

摘要

工业资产运营工作流对延迟高度敏感，因为单个用户查询可能需要协调传感器数据、工单、故障模式、预测工具以及领域特定智能体。我们在AssetOpsBench（AOB）上评估了这一问题，这是一个工业智能体基准测试，其计划-执行流水线反复暴露于工具发现、LLM规划、MCP工具执行和最终总结的开销中。现有的LLM缓存技术，如KV缓存复用和基于嵌入的语义缓存，是为聊天机器人服务设计的，当输出有效性依赖于时间、资产或传感器参数时，这些技术会失效。我们针对AOB计划-执行流水线提出了两个互补的优化层：一个时间语义缓存，以及一组MCP工作流优化，结合了基于磁盘的工具发现缓存和依赖感知的并行步骤执行。MCP工作流优化实现了1.67倍的加速，并将中位数端到端延迟降低约40.0%，而时间语义缓存在缓存命中时实现了30.6倍的中位数加速。除了加速效果外，我们的结果还揭示了纯语义缓存在参数丰富的工业查询中的一种具体失败模式，提供了关于缓存选择如何与基于MCP的智能体基准测试中的评估正确性相互作用的批判性分析。

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.