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:20260202T201809Z
LOCATION:274
DTSTART;TZID=America/Chicago:20251117T161000
DTEND;TZID=America/Chicago:20251117T163000
UID:submissions.supercomputing.org_SC25_sess215_ws_ai4s107@linklings.com
SUMMARY:InferA: A Smart Assistant for Cosmological Ensemble Data
DESCRIPTION:Justin Tam (Los Alamos National Laboratory (LANL)), Pascal Gro
 sset and Divya Banesh (Los Alamos National Laboratory), Nesar Ramachandra 
 (Argonne National Laboratory (ANL)), and Terece Turton and James Ahrens (L
 os Alamos National Laboratory)\n\nAnalyzing large-scale scientific dataset
 s presents substantial challenges due to their sheer volume, structural co
 mplexity, and the need for specialized domain knowledge. Automation tools,
  such as PandasAI, typically require full data ingestion and lack context 
 of the full data structure, making them impractical as intelligent data an
 alysis assistants for datasets at the terabyte scale. To overcome these li
 mitations, we propose InferA, a multi-agent system that leverages Large La
 nguage Models to enable scalable and efficient scientific data analysis. A
 t the core of the architecture is a supervisor agent that orchestrates a t
 eam of specialized agents responsible for distinct phases of the data retr
 ieval and analysis. The system engages interactively with users to elicit 
 their analytical intent and confirm query objectives, ensuring alignment b
 etween user goals and system actions. To demonstrate the framework usabili
 ty, we evaluate the system using ensemble runs from the HACC cosmology sim
 ulation which comprises several terabytes.\n\nRecording: Livestreamed, Rec
 orded\n\nRegistration Category: Technical Program Reg Pass, Workshop Reg P
 ass\n\nSession Chairs: Gokcen Kestor (Barcelona Supercomputing Center (BSC
 ); University of California, Merced); Dong Li (University of California, M
 erced); and Murali Emani (Argonne National Laboratory (ANL))\n\n
END:VEVENT
END:VCALENDAR
