[2511.00739] Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective

-->

Computer Science > Artificial Intelligence

arXiv:2511.00739 (cs)

[Submitted on 1 Nov 2025 (v1), last revised 16 Apr 2026 (this version, v3)]

Title:Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective

Authors:Ritik Raj, Souvik Kundu, Ishita Vohra, Hong Wang, Tushar Krishna<br>View a PDF of the paper titled Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective, by Ritik Raj and 4 other authors

View PDF<br>HTML (experimental)

Abstract:Agentic AI serving converts monolithic LLM-based inference to autonomous problem-solvers that can plan, call tools, perform reasoning, and adapt on the fly. Due to diverse task execution need, such serving heavily rely on heterogeneous CPU-GPU systems with majority of the external tools responsible for agentic capability, either run on or are orchestrated by the CPU.

Towards having a deeper understanding of its role, this paper aims to characterize and analyze the system bottlenecks introduced by agentic AI workloads from a largely overlooked CPU-centric perspective. We first present a compile-time characterization of agentic AI execution and choose representative workloads to capture the algorithmic diversity. We then perform runtime characterization of the representative workloads analyzing the end-to-end latency and throughput on two different hardware systems to isolate respective architectural bottlenecks. Based on the insights on the bottlenecks, we finally present two scheduling optimizations, namely, 1. CPU-Aware Overlapped Micro-Batching (COMB) and 2. Mixed Agentic Scheduling (MAS) on homogeneous and heterogeneous agentic workloads, respectively. In specific, these methods optimize for improved CPU-GPU concurrent utilization while reducing skewed resource allocation for heterogeneous execution. Experimental evaluations on the two hardware systems demonstrate the efficacy of COMB in yielding up to 1.7x lower P50 latency in standalone homogeneous workload execution and up to 3.9x/1.8x lower service/total latency under homogeneous open-loop load. Additionally, for heterogeneous open-loop load, MAS can reduce the total latency for minority request-type by up to 2.37x/2.49x at P50/P90 percentile.

Subjects:

Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA)

Cite as:<br>arXiv:2511.00739 [cs.AI]

(or<br>arXiv:2511.00739v3 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2511.00739

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Ritik Raj [view email]<br>[v1]<br>Sat, 1 Nov 2025 23:46:44 UTC (3,218 KB)

[v2]<br>Sat, 29 Nov 2025 15:45:25 UTC (3,218 KB)

[v3]<br>Thu, 16 Apr 2026 18:23:56 UTC (3,881 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective, by Ritik Raj and 4 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.AI

next >

new<br>recent<br>| 2025-11

Change to browse by:

cs<br>cs.LG<br>cs.MA

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs...