Evaluating Temporal Semantic Caching and Workflow Optimization in Agentic Plan-Execute Pipelines
Quick Answer
The study introduces a temporal semantic cache and MCP workflow optimizations for AssetOpsBench, achieving a 1.67x speedup and 40% latency reduction in industrial asset operations.
Quick Take
The temporal-cache benchmark demonstrated a remarkable 30.6x speedup on cache hits, highlighting the limitations of existing caching techniques in parameter-rich queries.
Key Points
- workflow optimizations led to a 1.67x speedup in execution.
- Median end-to-end latency reduced by approximately 40%.
- Temporal-cache benchmark achieved a 30.6x speedup on cache hits.
- Existing LLM caching techniques fail with time-sensitive industrial queries.
- Study provides critical insights into caching choices and evaluation correctness.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Comments: | 13 pages, 8 figures, 3 appendices |
| Subjects: | Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.11; H.3.4; C.4 |
| Cite as: | arXiv:2605.20630 [cs.AI] |
| (or arXiv:2605.20630v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.20630 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Krish Veera [view email]
[v1]
Wed, 20 May 2026 02:30:07 UTC (2,885 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.