BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260202T201809Z
LOCATION:240
DTSTART;TZID=America/Chicago:20251116T115500
DTEND;TZID=America/Chicago:20251116T122000
UID:submissions.supercomputing.org_SC25_sess119_ws_xloop107@linklings.com
SUMMARY:AI Agents for Enabling Autonomous Experiments at ORNL's HPC and Ma
 nufacturing User Facilities
DESCRIPTION:Daniel Rosendo, Stephen DeWitt, Renan Souza, Phillipe Austria,
  Tirthankar Ghosal, Marshall McDonnell, Ross Miller, Tyler Skluzacek, Jame
 s Haley, Bruno Turcksin, Jesse McGaha, Benjamin Mintz, Feiyi Wang, Mallika
 rjun Shankar, Sarp Oral, and Rafael Ferreira da Silva (Oak Ridge National 
 Laboratory (ORNL))\n\nThis paper presents a modular architecture for enabl
 ing autonomous cross-facility scientific experimentation using AI agents a
 t ORNL's HPC and manufacturing user facilities. The proposed system integr
 ates a natural language interface powered by an LLM, a multi-agent framewo
 rk for decision making, programmable facility APIs, and a provenance-aware
  infrastructure to support adaptive, explainable, and reproducible workflo
 ws. We demonstrate how AI agents can orchestrate and optimize additive man
 ufacturing experiments through near real-time coordination between experim
 ental 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 acc
 elerates the scientific discovery process.\n\nRecording: Livestreamed, Rec
 orded\n\nRegistration Category: Technical Program Reg Pass, Workshop Reg P
 ass\n\nSession Chairs: Justin Wozniak (Argonne National Laboratory (ANL), 
 University of Chicago); Nicholas Schwarz (Argonne National Laboratory (ANL
 )); and Hannah Parraga (Argonne National Laboratory (ANL))\n\n
END:VEVENT
END:VCALENDAR