Saved in:
Bibliographic Details
Main Authors: Mendoza, Sergio, Bhihe, Cedric, Zamora, Natalia, Modesto, David, Batalla, Jose Martin Bugallo, Canovas, Jesus Gomez, Avellaneda, Rafel Palomo, Espinosa, Miguel Perez
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.03743
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913090916843520
author Mendoza, Sergio
Bhihe, Cedric
Zamora, Natalia
Modesto, David
Batalla, Jose Martin Bugallo
Canovas, Jesus Gomez
Avellaneda, Rafel Palomo
Espinosa, Miguel Perez
author_facet Mendoza, Sergio
Bhihe, Cedric
Zamora, Natalia
Modesto, David
Batalla, Jose Martin Bugallo
Canovas, Jesus Gomez
Avellaneda, Rafel Palomo
Espinosa, Miguel Perez
contents Human involvement is critical in training and deploying AI systems in high-stakes defence and security contexts. However, real-time interaction is impractical in HPC environments due to compute intensity and resource constraints. We present a workflow framework that enables asynchronous human-AI collaboration across hybrid infrastructures, including HPC clusters, local machines, and cloud platforms. Workflows can pause at defined checkpoints for human input without halting underlying compute jobs, preventing idle resources and enabling non-blocking supervision. The framework supports interaction with SLURM-based scheduling, containerized and native tasks, and is customized for scenarios requiring human judgment and adaptability. We demonstrate its application in model training on systems like MareNostrum 5, highlighting benefits in portability, efficiency, and oversight in operational AI workflows.
format Preprint
id arxiv_https___arxiv_org_abs_2605_03743
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Workflow-Oriented Framework for Asynchronous Human-AI Collaboration in Hybrid and Compute-Intensive HPC Environments
Mendoza, Sergio
Bhihe, Cedric
Zamora, Natalia
Modesto, David
Batalla, Jose Martin Bugallo
Canovas, Jesus Gomez
Avellaneda, Rafel Palomo
Espinosa, Miguel Perez
Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Human-Computer Interaction
Software Engineering
Human involvement is critical in training and deploying AI systems in high-stakes defence and security contexts. However, real-time interaction is impractical in HPC environments due to compute intensity and resource constraints. We present a workflow framework that enables asynchronous human-AI collaboration across hybrid infrastructures, including HPC clusters, local machines, and cloud platforms. Workflows can pause at defined checkpoints for human input without halting underlying compute jobs, preventing idle resources and enabling non-blocking supervision. The framework supports interaction with SLURM-based scheduling, containerized and native tasks, and is customized for scenarios requiring human judgment and adaptability. We demonstrate its application in model training on systems like MareNostrum 5, highlighting benefits in portability, efficiency, and oversight in operational AI workflows.
title A Workflow-Oriented Framework for Asynchronous Human-AI Collaboration in Hybrid and Compute-Intensive HPC Environments
topic Distributed, Parallel, and Cluster Computing
Artificial Intelligence
Human-Computer Interaction
Software Engineering
url https://arxiv.org/abs/2605.03743