Papers
arxiv:2605.20630

Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines

Published on May 20
· Submitted by
Dhaval Patel
on May 21
Authors:
,
,

Abstract

Industrial asset operations workflows face latency challenges due to complex coordination needs, addressed through novel caching and workflow optimization techniques that improve execution speed while maintaining correctness in parameter-rich environments.

AI-generated summary

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.

Community

Paper author Paper submitter

Industrial asset operations workflows are latency-sensitive because a single user
query may require coordination over sensor data, work orders, failure modes, fore-
casting tools, and domain-specific agents. We evaluate this problem on Asse-
tOpsBench (AOB), an industrial agent benchmark whose plan-execute pipeline
exposes repeated overhead from tool discovery, LLM planning, MCP tool exe-
cution, 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 sen-
sor 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
1.67× speedup and reduced median end-to-end latency by about 40.0% while the
temporal-cache benchmark achieved a median of 30.6× speedup on cache hits.
Beyond the speedup, our results expose a concrete failure mode of pure seman-
tic caching for parameter-rich industrial queries, providing a critical analysis of
how caching choices interact with evaluation correctness in MCP-backed agent
benchmarks.

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.20630
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.20630 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.20630 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.20630 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.