Workshops Archive

Diamond Agent: Agentic Control of Federated HPC Resources as a Service


Workshop: AgenticAI4HPC’26: The First International Workshop on Agentic AI for HPC

Authors: Haotian Xie, Junlin Chen, and Mingkai Zheng (Rutgers University); Yifan Zhu (University of Rochester); Minu Mathew and Max Burnette (University of Illinois at Urbana-Champaign); Yadu Babuji (University of Chicago, Argonne National Laboratory); Volodymyr Kindratenko (University of Illinois at Urbana-Champaign); Shivaram Venkataraman (University of Wisconsin-Madison); Kyle Chard and Ian Foster (University of Chicago, Argonne National Laboratory); and Zhao Zhang (Rutgers University)

Abstract: Efficiently aggregating and orchestrating computing power across heterogeneous clusters for HPC workflows faces four practical challenges: preserving workflow context across independently administered clusters, moving large datasets between sites, reasoning about site-specific environments and scheduler policies, and exploiting live queue and resource states for efficient task scheduling. To this end, we design Diamond Agent, an agentic system that enables intelligent execution of HPC workflows across heterogeneous clusters. Diamond Agent provides an agent-facing workspace and skills that unify cross-site resource discovery, resource specification, data movement, task execution, and result retrieval. Diamond Agent translates high-level agent actions into valid site-specific executions, moves data through Globus Transfer, and uses live system capability and queue information to select feasible placements. Its event-driven continuation mechanism decouples agent actions from long-running batch jobs: persistent services monitor remote execution and resume the agent only when a result or decision-relevant event is available.


Back to AgenticAI4HPC’26: The First International Workshop on Agentic AI for HPC Archive Listing

Back to Full Workshop Archive Listing