BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260611T145141Z
LOCATION:Bldg. 6 - Room 102
DTSTART;TZID=Europe/Stockholm:20260701T103000
DTEND;TZID=Europe/Stockholm:20260701T110000
UID:submissions.pasc-conference.org_PASC26_sess152_msa189@linklings.com
SUMMARY:Workflow-Centric Co-Design for Trustworthy, Agentic Exascale Scien
 ce
DESCRIPTION:Patrick Widener (Oak Ridge National Laboratory)\n\nExascale sy
 stems enable unprecedented computational power, but scientific impact depe
 nds on workflows that jointly deliver performance, trust, and scalability.
  This talk presents a workflow-centric co-design perspective in which work
 flows are treated as first-class abstractions for aligning architecture, s
 oftware, data, and algorithms. Building on recent advances in agentic and 
 agent-based workflows, the talk explores how intelligent agents embedded w
 ithin workflows can reason about data, performance, and scientific objecti
 ves while preserving reproducibility and validation guarantees. Drawing fr
 om U.S. DOE science use cases, we show how agentic workflows enable adapti
 ve orchestration, automated data staging, and AI-aware decision-making acr
 oss heterogeneous HPC environments. Agents extend traditional workflows fr
 om static pipelines toward learning, optimizing, and cooperative execution
  models, supporting resilience, energy efficiency, and predictable perform
 ance required by operational workloads such as digital twins. By framing a
 gents as an evolutionary extension of established workflow systems rather 
 than a disruptive replacement, this talk highlights a practical co-design 
 path toward scalable, trustworthy, and AI-ready exascale science.\n\nDomai
 n: Climate, Weather, and Earth Sciences, Computational Methods and Applied
  Mathematics\n\nSession Chairs: Ali Mohammed (HPE), Florina Ciorba (Univer
 sity of Basel), and Utz-Uwe Haus (HPE HPC/AI EMEA Research Lab)\n\n
END:VEVENT
END:VCALENDAR