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:20260202T201808Z
LOCATION:241
DTSTART;TZID=America/Chicago:20251116T160000
DTEND;TZID=America/Chicago:20251116T163000
UID:submissions.supercomputing.org_SC25_sess209_ws_fgai105@linklings.com
SUMMARY:LABMATE: Language Model Based Multi-Agent System to Accelerate Cat
 alysis Experiments
DESCRIPTION:Anurag Acharya (Pacific Northwest National Laboratory (PNNL));
  Anshu Kiran Sharma (Florida International University, Pacific Northwest N
 ational Laboratory (PNNL)); and Derek Parker, Timothy Vega, Rizwan A. Ashr
 af, Natalie M. Isenberg, Jan Strube, and Robert Rallo (Pacific Northwest N
 ational Laboratory (PNNL))\n\nLarge Language Models (LLMs) are unreliable 
 to make decisions due to their potential to hallucinate, and unable to per
 form complex tasks like running simulations essential to fields like Mater
 ial Science. We introduce LABMATE (LAnguage model Based Multi-agent system
  to Accelerate caTalysis Experiments), a human-in-the-loop copilot framewo
 rk that utilizes LLM agents to make catalysis research faster. LABMATE all
 ows human experts to run simulations, track particle sizes, run data analy
 sis, conduct literature review, and generate potential hypothesis all in o
 ne framework, thereby expediting the research process. When evaluated on t
 he major benchmarks, LABMATE performs comparable to or better than most fr
 ontier LLMs, showing that in addition to accelerating the experimental pro
 cess, our framework is also on par in domain knowledge compared to using a
  simple LLM. Furthermore, since the core architecture of the system is dom
 ain-agnostic, it can easily be adapted to other domains.\n\nRecording: Liv
 estreamed, Recorded\n\nRegistration Category: Technical Program Reg Pass, 
 Workshop Reg Pass\n\nSession Chairs: Charlie Catlett (Argonne National Lab
 oratory (ANL), University of Chicago); Javier Aula-Blasco (Barcelona Super
 computing Center (BSC)); Valerie Taylor (Argonne National Laboratory (ANL)
 , University of Chicago); Laura Morselli (CINECA); and Rio Yokota (Institu
 te of Science Tokyo)\n\n
END:VEVENT
END:VCALENDAR