Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines
For developers of latency-sensitive industrial agent pipelines, the paper provides concrete optimizations and exposes failure modes of existing caching techniques.
The paper tackles latency in industrial asset operations workflows by proposing temporal semantic caching and MCP workflow optimizations, achieving a 1.67x speedup and 40% latency reduction from workflow optimizations, and a 30.6x speedup on cache hits from temporal caching.
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.