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:20260421T090512Z
LOCATION:Bldg. 8 - Room 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:Advances in agentic AI—autonomous, tool-using systems that pla
 n, call simulators, reason over uncertainty, and adapt—are poised to trans
 form how we explore vast chemical and materials design spaces. This minisy
 mposium will showcase state-of-the-art methods that couple agentic decisio
 n-making with scalable HPC workflows to accelerate hypothesis generation, 
 simulation throughput, and autonomy while strengthening scientific trust. 
 Topics span agent-driven hypothesis generation and assessment, automatic e
 xecution of large computational campaigns based on different simulation sc
 ales, and workflow/runtime systems that autonomously schedule thousands to
  millions of tasks across heterogeneous supercomputers with robust provena
 nce and reproducibility. A central thread is Building Trust in Science thr
 ough HPC Co-Design: contributors will detail how agents, numerical methods
 , software stacks, data services, are co-designed to deliver validated, re
 producible, and/or auditable results using autonomous loops.\n\nAccelerati
 ng Molecular Discovery with AI Agents\n\nChemistry underpins many fields c
 ritical to modern society, yet the rational design of chemical systems wit
 h targeted properties remains a formidable challenge due to the immense si
 ze of chemical space.  Typical examples include the development of selecti
 ve reagents for metal separations and robust ...\n\n\nDanny Perez (Los Ala
 mos National Laboratory)\n---------------------\nSemantic Provenance for T
 rustworthy Agentic Workflows in Materials Science\n\nAgentic AI systems, a
 utonomous agents capable of planning simulations, invoking computational t
 ools, and reasoning over results, offer new opportunities for accelerating
  discovery in materials science. However, ensuring reproducibility of rese
 arch endeavors remains a key challenge when autonomous sy...\n\n\nEdan Bai
 nglass, Xing Wang, Alexander Goscinski, Julian Geiger, and Giovanni Pizzi 
 (Paul Scherrer Institute)\n---------------------\nSelf-Validating Research
  Assistant for High Performance Electronic Structure Calculations\n\nAgent
 ic AI systems based on large language models (LLMs) offer promising avenue
 s for automating atomistic modeling workflows on high-performance computin
 g (HPC) platforms. However, incorrect workflow specification in this conte
 xt can lead to substantial computational waste and unreliable scientific .
 ..\n\n\nLuigi Genovese (CEA Grenoble)\n---------------------\npyiron – A w
 orkflow framework for trustworthy agentic workflows in materials science\n
 \nThe hierarchical nature of materials requires simulation approaches that
  couple methods across disciplines and length scales. Integrating heteroge
 neous simulation codes poses significant interoperability challenges due t
 o incompatible units, file formats, and data structures. The pyiron workfl
 ow fra...\n\n\nJan Janssen (Max-Planck-Insitute for Sustainable Materials)
 \n\nDomain: Chemistry and Materials, Climate, Weather, and Earth Sciences,
  Engineering, Physics\n\nSession Chair: Jan Janssen (Max Planck Institute 
 for Sustainable Materials)
END:VEVENT
END:VCALENDAR