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:20260202T201805Z
LOCATION:241
DTSTART;TZID=America/Chicago:20251116T113000
DTEND;TZID=America/Chicago:20251116T120000
UID:submissions.supercomputing.org_SC25_sess209_ws_fgai126@linklings.com
SUMMARY:GridMind: LLMs-Powered Agents for Power System Analysis and Operat
 ions
DESCRIPTION:Hongwei Jin, Kibaek Kim, and Jonghwan Kwon (Argonne National L
 aboratory (ANL))\n\nThe complexity of traditional power system analysis wo
 rkflows presents significant barriers to efficient decision-making in mode
 rn electric grids. This paper presents GridMind, a multi-agent AI system t
 hat integrates Large Language Models (LLMs) with deterministic engineering
  solvers to enable conversational scientific computing for power system an
 alysis. The system employs specialized agents coordinating AC Optimal Powe
 r Flow and N-1 contingency analysis through natural language interfaces wh
 ile maintaining numerical precision via function calls. GridMind addresses
  workflow integration, knowledge accessibility, context preservation, and 
 expert decision-support augmentation. Experimental evaluation on IEEE test
  cases demonstrates that the proposed agentic framework consistently deliv
 ers correct solutions across all tested language models, with smaller LLMs
  achieving comparable analytical accuracy with reduced computational laten
 cy. This work establishes agentic AI as a viable paradigm for scientific c
 omputing, demonstrating how conversational interfaces can enhance accessib
 ility while preserving numerical rigor essential for critical engineering 
 applications.\n\nRecording: Livestreamed, Recorded\n\nRegistration Categor
 y: Technical Program Reg Pass, Workshop Reg Pass\n\nSession Chairs: Charli
 e Catlett (Argonne National Laboratory (ANL), University of Chicago); Javi
 er Aula-Blasco (Barcelona Supercomputing Center (BSC)); Valerie Taylor (Ar
 gonne National Laboratory (ANL), University of Chicago); Laura Morselli (C
 INECA); and Rio Yokota (Institute of Science Tokyo)\n\n
END:VEVENT
END:VCALENDAR