BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//modelica.simtek.cc//amfc2026//speaker//L9Z8BL
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:CST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-amfc2026-J78WAX@modelica.simtek.cc
DTSTART;TZID=CST:20260921T160000
DTEND;TZID=CST:20260921T162500
DESCRIPTION:In this work\, we compare a traditional design-ofexperiments (D
 oE) workflow\, defined up-front and then run\, against an agentic AI workf
 low that revises its plan as the data arrives. The use case is a chassis o
 ptimization on the standard compact example in the Modelon VehicleDynamics
  Library. Both workflows produce a recommendation. The DoE arrives at a cl
 ean Pareto front and a stiffness change. The agentic path is longer: along
  the way it flags a controller saturation in the DoE winner\, traces a cen
 ter-ofgravity asymmetry to a load sensitivity the original scope did not c
 over\, and finds a kinematic ceiling outside the four DoE parameters. It e
 nds up changing a different parameter\, and that parameter turns out to do
  more than the static KPIs asked for: dynamic verification shows the bushi
 ng change roughly halves the fishhook return lag unloaded. The architectur
 e that makes this possible combines validated physics\, Modelon Impact\, t
 he Model Context Protocol that connects them to an LLM\, and a knowledge b
 ase layered by lifetime. We close with what we learned about when each app
 roach is the right tool.
DTSTAMP:20261004T070757Z
LOCATION:Modelica Technology & AI (R1001)
SUMMARY:From Intent to Action: Agentic AI on Validated Modelica Libraries -
  Johan Andreasson\, Ajith Kumar\, Clément Coïc
URL:https://modelica.simtek.cc/amfc2026/talk/J78WAX/
END:VEVENT
END:VCALENDAR