[2605.02162] AAFLOW: Scalable Patterns for Agentic AI Workflows

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Distributed, Parallel, and Cluster Computing

arXiv:2605.02162 (cs)

[Submitted on 4 May 2026]

Title:AAFLOW: Scalable Patterns for Agentic AI Workflows

Authors:Arup Kumar Sarker, Mills Staylor, Aymen Alsaadi, Gregor von Laszewski, Shantenu Jha, Geoffrey Fox<br>View a PDF of the paper titled AAFLOW: Scalable Patterns for Agentic AI Workflows, by Arup Kumar Sarker and 5 other authors

View PDF<br>HTML (experimental)

Abstract:Agentic workflows in large language model systems integrate retrieval, reasoning, and memory, but existing frameworks suffer from scalability and reproducibility limitations due to fragmented data orchestration, serialization overhead, and non-deterministic execution. Although these frameworks increase flexibility, they don't have a formal execution model that adheres to the principles of high-performance computing. We introduce AAFLOW, a unified distributed runtime that creates communication-efficient execution plans by modeling agentic workflows as an operator abstraction. Using Apache Arrow and Cylon, AAFLOW creates a zero-copy data plane that allows direct interoperability between preprocessing, embedding, and vector retrieval without the need for serialization overhead. To lower coordination costs, it uses resource-deterministic scheduling and asynchronous batching. While retaining comparable LLM generation throughput, experimental results demonstrate up to 4.64 times pipeline speedup and 2.8 times gains in embedding and upsert phases. Rather than LLM inference acceleration, these advantages result from enhanced data flow, batching, and communication efficiency.

Comments:<br>10 pages, 8 Figures, 3 Tables. preprint for SC2026

Subjects:

Distributed, Parallel, and Cluster Computing (cs.DC); Multiagent Systems (cs.MA)

ACM classes:<br>F.2.2; I.2.7

Cite as:<br>arXiv:2605.02162 [cs.DC]

(or<br>arXiv:2605.02162v1 [cs.DC] for this version)

https://doi.org/10.48550/arXiv.2605.02162

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Arup Kumar Sarker [view email]<br>[v1]<br>Mon, 4 May 2026 02:39:13 UTC (4,506 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled AAFLOW: Scalable Patterns for Agentic AI Workflows, by Arup Kumar Sarker and 5 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.DC

next >

new<br>recent<br>| 2026-05

Change to browse by:

cs<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 .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)

Major funding support from