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:20260724T151408Z
LOCATION:Bldg. 8 - B 102
DTSTART;TZID=Europe/Stockholm:20260701T090000
DTEND;TZID=Europe/Stockholm:20260701T110000
UID:submissions.pasc-conference.org_PASC26_sess157@linklings.com
SUMMARY:MS4H - Agentic Workflows for Trustworthy Discovery in Materials Sc
 ience and Chemistry
DESCRIPTION:Access the recording\n\nOrganizer(s): Jan Janssen (Max Planck 
 Institute for Sustainable Materials)\n\nAdvances in agentic AI—autonomous,
  tool-using systems that plan, call simulators, reason over uncertainty, a
 nd adapt—are poised to transform how we explore vast chemical and material
 s design spaces. This minisymposium will showcase state-of-the-art methods
  that couple agentic decision-making with scalable HPC workflows to accele
 rate hypothesis generation, simulation throughput, and autonomy while stre
 ngthening scientific trust. Topics span agent-driven hypothesis generation
  and assessment, automatic execution of large computational campaigns base
 d on different simulation scales, and workflow/runtime systems that autono
 mously schedule thousands to millions of tasks across heterogeneous superc
 omputers with robust provenance and reproducibility. A central thread is B
 uilding Trust in Science through HPC Co-Design: contributors will detail h
 ow agents, numerical methods, software stacks, data services, are co-desig
 ned to deliver validated, reproducible, and/or auditable results using aut
 onomous loops.\n\nAccelerating Molecular Discovery with AI Agents\n\nChemi
 stry underpins many fields critical to modern society, yet the rational de
 sign of chemical systems with targeted properties remains a formidable cha
 llenge due to the immense size of chemical space.  Typical examples includ
 e the development of selective reagents for metal separations and robust .
 ..\n\n\nDanny Perez (Los Alamos National Laboratory)\n--------------------
 -\nSemantic Provenance for Trustworthy Agentic Workflows in Materials Scie
 nce\n\nAgentic AI systems, autonomous agents capable of planning simulatio
 ns, invoking computational tools, and reasoning over results, offer new op
 portunities for accelerating discovery in materials science. However, ensu
 ring reproducibility of research endeavors remains a key challenge when au
 tonomous sy...\n\n\nEdan Bainglass, Xing Wang, Alexander Goscinski, Julian
  Geiger, and Giovanni Pizzi (Paul Scherrer Institute)\n-------------------
 --\nSelf-Validating Research Assistant for High Performance Electronic Str
 ucture Calculations\n\nAgentic AI systems based on large language models (
 LLMs) offer promising avenues for automating atomistic modeling workflows 
 on high-performance computing (HPC) platforms. However, incorrect workflow
  specification in this context can lead to substantial computational waste
  and unreliable scientific ...\n\n\nLuigi Genovese (CEA Grenoble)\n-------
 --------------\npyiron – A Workflow Framework for Trustworthy Agentic Work
 flows in Materials Science\n\nThe hierarchical nature of materials require
 s simulation approaches that couple methods across disciplines and length 
 scales. Integrating heterogeneous simulation codes poses significant inter
 operability challenges due to incompatible units, file formats, and data s
 tructures. The pyiron workflow fra...\n\n\nJan Janssen (Max-Planck-Insitut
 e for Sustainable Materials)\n\nDomain: Chemistry and Materials, Climate, 
 Weather, and Earth Sciences, Engineering, Physics\n\nSession Chair: Jan Ja
 nssen (Max Planck Institute for Sustainable Materials)
END:VEVENT
END:VCALENDAR