AI Agents for Enabling Autonomous Experiments at ORNL’s HPC and Manufacturing User Facilities

Daniel Rosendo; Stephen DeWitt; Renan Souza; Phillipe Austria; Tirthankar Ghosal; Marshall McDonnell; Ross Miller; Tyler Skluzacek; James Haley; Bruno Turcksin; Jesse McGaha; Benjamin Mintz; Feiyi Wang; Mallikarjun Shankar; Sarp Oral; Rafael Ferreira da Silva

doi:10.1145/3731599.3767592

AI Agents for Enabling Autonomous Experiments at ORNL’s HPC and Manufacturing User Facilities

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper presents a modular architecture for enabling autonomous cross-facility scientific experimentation using AI agents at ORNL’s HPC and manufacturing user facilities. The proposed system integrates a natural language interface powered by an LLM, a multi-agent framework for decision making, programmable facility APIs, and a provenance-aware infrastructure to support adaptive, explainable, and reproducible workflows. We demonstrate how AI agents can orchestrate and optimize additive manufacturing experiments through near real-time coordination between experimental and HPC resources. The architecture is evaluated through a realistic end-to-end workflow that employs a simulated version of the manufacturing facility, showing that the approach reduces coordination overhead and accelerates the scientific discovery process.

Original language	English
Title of host publication	Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops
Publisher	Association for Computing Machinery, Inc
Pages	2354-2361
Number of pages	8
ISBN (Electronic)	9798400718717
DOIs	https://doi.org/10.1145/3731599.3767592
State	Published - Nov 15 2025
Event	2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops - St. Louis, United States Duration: Nov 16 2025 → Nov 21 2025

Publication series

Name	Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops

Conference

Conference	2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops
Country/Territory	United States
City	St. Louis
Period	11/16/25 → 11/21/25

Funding

This research used resources of the Oak Ridge Leadership Compute Facility and ORNL Research Cloud Infrastructure at ORNL, which is supported by DOE’s Office of Science under Contract No. DE-AC05-00OR22725.

Keywords

AI Agents
Autonomous Scientific Workflows
Cross-Facility Orchestration
Experiment Steering

Access to Document

10.1145/3731599.3767592

Cite this

Rosendo, D., DeWitt, S., Souza, R., Austria, P., Ghosal, T., McDonnell, M., Miller, R., Skluzacek, T., Haley, J., Turcksin, B., McGaha, J., Mintz, B., Wang, F., Shankar, M., Oral, S., & da Silva, R. F. (2025). AI Agents for Enabling Autonomous Experiments at ORNL’s HPC and Manufacturing User Facilities. In Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops (pp. 2354-2361). (Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops). Association for Computing Machinery, Inc. https://doi.org/10.1145/3731599.3767592

Rosendo, Daniel ; DeWitt, Stephen ; Souza, Renan et al. / AI Agents for Enabling Autonomous Experiments at ORNL’s HPC and Manufacturing User Facilities. Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops. Association for Computing Machinery, Inc, 2025. pp. 2354-2361 (Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops).

@inproceedings{08b5450fdba047149ef7def97fa884c2,

title = "AI Agents for Enabling Autonomous Experiments at ORNL{\textquoteright}s HPC and Manufacturing User Facilities",

abstract = "This paper presents a modular architecture for enabling autonomous cross-facility scientific experimentation using AI agents at ORNL{\textquoteright}s HPC and manufacturing user facilities. The proposed system integrates a natural language interface powered by an LLM, a multi-agent framework for decision making, programmable facility APIs, and a provenance-aware infrastructure to support adaptive, explainable, and reproducible workflows. We demonstrate how AI agents can orchestrate and optimize additive manufacturing experiments through near real-time coordination between experimental and HPC resources. The architecture is evaluated through a realistic end-to-end workflow that employs a simulated version of the manufacturing facility, showing that the approach reduces coordination overhead and accelerates the scientific discovery process.",

keywords = "AI Agents, Autonomous Scientific Workflows, Cross-Facility Orchestration, Experiment Steering",

author = "Daniel Rosendo and Stephen DeWitt and Renan Souza and Phillipe Austria and Tirthankar Ghosal and Marshall McDonnell and Ross Miller and Tyler Skluzacek and James Haley and Bruno Turcksin and Jesse McGaha and Benjamin Mintz and Feiyi Wang and Mallikarjun Shankar and Sarp Oral and \{da Silva\}, \{Rafael Ferreira\}",

note = "Publisher Copyright: {\textcopyright} 2025 Copyright held by the owner/author(s).; 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops ; Conference date: 16-11-2025 Through 21-11-2025",

year = "2025",

month = nov,

day = "15",

doi = "10.1145/3731599.3767592",

language = "English",

series = "Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops",

publisher = "Association for Computing Machinery, Inc",

pages = "2354--2361",

booktitle = "Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops",

}

Rosendo, D , DeWitt, S, Souza, R, Austria, P , Ghosal, T , McDonnell, M , Miller, R , Skluzacek, T , Haley, J , Turcksin, B, McGaha, J, Mintz, B, Wang, F , Shankar, M , Oral, S & da Silva, RF 2025, AI Agents for Enabling Autonomous Experiments at ORNL’s HPC and Manufacturing User Facilities. in Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops. Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops, Association for Computing Machinery, Inc, pp. 2354-2361, 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops, St. Louis, United States, 11/16/25. https://doi.org/10.1145/3731599.3767592

AI Agents for Enabling Autonomous Experiments at ORNL’s HPC and Manufacturing User Facilities. / Rosendo, Daniel ; DeWitt, Stephen; Souza, Renan et al.
Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops. Association for Computing Machinery, Inc, 2025. p. 2354-2361 (Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - AI Agents for Enabling Autonomous Experiments at ORNL’s HPC and Manufacturing User Facilities

AU - Rosendo, Daniel

AU - DeWitt, Stephen

AU - Souza, Renan

AU - Austria, Phillipe

AU - Ghosal, Tirthankar

AU - McDonnell, Marshall

AU - Miller, Ross

AU - Skluzacek, Tyler

AU - Haley, James

AU - Turcksin, Bruno

AU - McGaha, Jesse

AU - Mintz, Benjamin

AU - Wang, Feiyi

AU - Shankar, Mallikarjun

AU - Oral, Sarp

AU - da Silva, Rafael Ferreira

PY - 2025/11/15

Y1 - 2025/11/15

N2 - This paper presents a modular architecture for enabling autonomous cross-facility scientific experimentation using AI agents at ORNL’s HPC and manufacturing user facilities. The proposed system integrates a natural language interface powered by an LLM, a multi-agent framework for decision making, programmable facility APIs, and a provenance-aware infrastructure to support adaptive, explainable, and reproducible workflows. We demonstrate how AI agents can orchestrate and optimize additive manufacturing experiments through near real-time coordination between experimental and HPC resources. The architecture is evaluated through a realistic end-to-end workflow that employs a simulated version of the manufacturing facility, showing that the approach reduces coordination overhead and accelerates the scientific discovery process.

AB - This paper presents a modular architecture for enabling autonomous cross-facility scientific experimentation using AI agents at ORNL’s HPC and manufacturing user facilities. The proposed system integrates a natural language interface powered by an LLM, a multi-agent framework for decision making, programmable facility APIs, and a provenance-aware infrastructure to support adaptive, explainable, and reproducible workflows. We demonstrate how AI agents can orchestrate and optimize additive manufacturing experiments through near real-time coordination between experimental and HPC resources. The architecture is evaluated through a realistic end-to-end workflow that employs a simulated version of the manufacturing facility, showing that the approach reduces coordination overhead and accelerates the scientific discovery process.

KW - AI Agents

KW - Autonomous Scientific Workflows

KW - Cross-Facility Orchestration

KW - Experiment Steering

UR - https://www.scopus.com/pages/publications/105023401307

U2 - 10.1145/3731599.3767592

DO - 10.1145/3731599.3767592

M3 - Conference contribution

AN - SCOPUS:105023401307

T3 - Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops

SP - 2354

EP - 2361

BT - Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops

PB - Association for Computing Machinery, Inc

T2 - 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops

Y2 - 16 November 2025 through 21 November 2025

ER -

Rosendo D , DeWitt S, Souza R, Austria P , Ghosal T , McDonnell M et al. AI Agents for Enabling Autonomous Experiments at ORNL’s HPC and Manufacturing User Facilities. In Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops. Association for Computing Machinery, Inc. 2025. p. 2354-2361. (Proceedings of 2025 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, SC 2025 Workshops). doi: 10.1145/3731599.3767592

AI Agents for Enabling Autonomous Experiments at ORNL’s HPC and Manufacturing User Facilities

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this