BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20250309T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260124T050510Z
UID:052C2CEC-6E7F-4A54-9E48-4EEE0565F17F
DTSTART;TZID=America/New_York:20250605T180000
DTEND;TZID=America/New_York:20250605T190000
DESCRIPTION:Special Presentation by Fan Liu (Washington U. in St. Louis\, U
 SA)\n\nHosted by the Future Networks Artificial Intelligence &amp; Machine Lea
 rning (AIML) Working Group\n\nDate/Time: Thursday\, 5 June 2025 @ 6 PM EDT
 \n\nTopic:\n\nBeyond the Buzz: What Large Language Models Actually Do (and
  Don’t Do) in Network\nAutomation\n\nAbstract:\n\nLarge Language Models 
 (LLMs) are increasingly explored for automating network operations and man
 agement — from translating intents to generating device configurations. 
 But how well do they actually perform? In this talk\, I share insights fro
 m a recent survey at the intersection of LLMs and computer networking. Rat
 her than covering every application\, I focus on one of the most active ar
 eas: network automation. I will walk through representative use cases\, hi
 ghlight current limitations\, and discuss what is still missing. The talk 
 concludes with a short research roadmap and open questions for making LLM-
 based automation more trustworthy and practical in real-world networks.\n\
 nSpeaker:\n\n[]\nFan Liu is a second-year Ph.D. student in Computer Scienc
 e at Washington University in St.\nLouis. Her research focuses on applying
  artificial intelligence to computer network operations\nand management\, 
 with an emphasis on large language models (LLMs). She is the first author 
 of a\nrecent survey on LLM applications in network operations\, currently 
 available as a preprint. Fan\nis also exploring LLM-driven approaches to a
 utomate incident response workflows. Her broader\ninterests include using 
 AI to enhance the infrastructure and applications of next-generation\nnetw
 orks.\n\nCo-sponsored by: Future Networks Artificial Intelligence &amp; Machin
 e Learning (AIML) Working Group\n\nVirtual: https://events.vtools.ieee.org
 /m/484809
LOCATION:Virtual: https://events.vtools.ieee.org/m/484809
ORGANIZER:baw@ieee.org
SEQUENCE:34
SUMMARY:What LLMs Actually Do in Network Automation
URL;VALUE=URI:https://events.vtools.ieee.org/m/484809
X-ALT-DESC:Description: &lt;br /&gt;&lt;p class=&quot;MsoNormal&quot; style=&quot;margin-top: .25in
 \;&quot;&gt;&lt;img src=&quot;https://events.vtools.ieee.org/vtools_ui/media/display/cff97
 1b1-135b-4d2c-984a-60b606f77a57&quot; width=&quot;750&quot; height=&quot;197&quot;&gt;&lt;/p&gt;\n&lt;p class=&quot;
 MsoNormal&quot; style=&quot;margin-top: 12.0pt\;&quot;&gt;Special Presentation by&lt;strong&gt; Fa
 n Liu (Washington U. in St. Louis\, USA)&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal
 &quot; style=&quot;margin-top: 12.0pt\;&quot;&gt;Hosted by the Future Networks&lt;strong&gt; Artif
 icial Intelligence &amp;amp\; Machine Learning (AIML) Working Group&lt;/strong&gt;&lt;/
 p&gt;\n&lt;p class=&quot;MsoNormal&quot; style=&quot;margin-top: 12.0pt\;&quot;&gt;&lt;strong&gt;&lt;span style=
 &quot;font-size: 14.0pt\; font-family: Copperplate\; mso-fareast-font-family: P
 MingLiU\; mso-fareast-theme-font: minor-fareast\; mso-bidi-font-family: Ar
 ial\; mso-bidi-theme-font: minor-bidi\; mso-ansi-language: EN-US\; mso-far
 east-language: ZH-TW\; mso-bidi-language: AR-SA\;&quot;&gt;Date/Time&lt;/span&gt;&lt;/stron
 g&gt;&lt;span style=&quot;font-size: 12.0pt\; font-family: &#39;Calibri&#39;\,sans-serif\; ms
 o-ascii-theme-font: minor-latin\; mso-fareast-font-family: PMingLiU\; mso-
 fareast-theme-font: minor-fareast\; mso-hansi-theme-font: minor-latin\; ms
 o-bidi-font-family: Arial\; mso-bidi-theme-font: minor-bidi\; mso-ansi-lan
 guage: EN-US\; mso-fareast-language: ZH-TW\; mso-bidi-language: AR-SA\;&quot;&gt;:
  &lt;strong&gt;Thursday\, 5 June 2025&lt;/strong&gt;&lt;strong&gt; @ 6 PM EDT&lt;/strong&gt;&lt;/span
 &gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot; style=&quot;margin-top: .25in\;&quot;&gt;&lt;strong&gt;&lt;u&gt;&lt;span s
 tyle=&quot;font-size: 16.0pt\; font-family: Copperplate\;&quot;&gt;Topic&lt;/span&gt;&lt;/u&gt;&lt;/st
 rong&gt;&lt;strong&gt;&lt;span style=&quot;font-size: 16.0pt\; font-family: Copperplate\;&quot;&gt;
 :&lt;/span&gt;&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;&lt;strong&gt;&lt;span style=&quot;font-size
 : 16.0pt\;&quot;&gt;Beyond the Buzz: What Large Language Models Actually Do (and D
 on&amp;rsquo\;t Do) in Network&lt;br&gt;Automation&lt;/span&gt;&lt;/strong&gt;&lt;/p&gt;\n&lt;p class=&quot;Ms
 oNormal&quot; style=&quot;margin-top: .25in\;&quot;&gt;&lt;strong&gt;&lt;u&gt;&lt;span style=&quot;font-size: 16
 .0pt\; font-family: Copperplate\;&quot;&gt;Abstract&lt;/span&gt;&lt;/u&gt;&lt;/strong&gt;&lt;strong&gt;&lt;sp
 an style=&quot;font-size: 16.0pt\; font-family: Copperplate\;&quot;&gt;:&lt;/span&gt;&lt;/strong
 &gt;&lt;/p&gt;\n&lt;p class=&quot;MsoNormal&quot;&gt;Large Language Models (LLMs) are increasingly 
 explored for automating network operations&amp;nbsp\;and management &amp;mdash\; f
 rom translating intents to generating device configurations. But how well 
 do&amp;nbsp\;they actually perform? In this talk\, I share insights from a rec
 ent survey at the intersection of&amp;nbsp\;LLMs and computer networking. Rath
 er than covering every application\, I focus on one of the&amp;nbsp\;most acti
 ve areas: network automation. I will walk through representative use cases
 \, highlight current limitations\, and discuss what is still missing. The 
 talk concludes with a short research roadmap and open questions for making
  LLM-based automation more trustworthy and practical&amp;nbsp\;in real-world n
 etworks.&lt;/p&gt;\n&lt;p&gt;&lt;strong&gt;&lt;span style=&quot;font-size: 16.0pt\; font-family: Cop
 perplate\;&quot;&gt;&lt;u&gt;Speaker&lt;/u&gt;:&lt;/span&gt;&lt;/strong&gt;&lt;/p&gt;\n&lt;table style=&quot;border-coll
 apse: collapse\; width: 100%\;&quot; border=&quot;1&quot;&gt;&lt;colgroup&gt;&lt;col style=&quot;width: 21
 .017274%\;&quot;&gt;&lt;col style=&quot;width: 78.886756%\;&quot;&gt;&lt;/colgroup&gt;\n&lt;tbody&gt;\n&lt;tr&gt;\n&lt;
 td&gt;&lt;img src=&quot;https://events.vtools.ieee.org/vtools_ui/media/display/50da8e
 a4-8b07-4e55-b633-a29d5a64e2cd&quot; alt=&quot;&quot; width=&quot;170&quot; height=&quot;203&quot;&gt;&lt;/td&gt;\n&lt;td
 &gt;\n&lt;p class=&quot;MsoNormal&quot; style=&quot;margin-top: 6.0pt\;&quot;&gt;Fan Liu is a second-ye
 ar Ph.D. student in Computer Science at Washington University in St.&lt;br&gt;Lo
 uis. Her research focuses on applying artificial intelligence to computer 
 network operations&lt;br&gt;and management\, with an emphasis on large language 
 models (LLMs). She is the first author of a&lt;br&gt;recent survey on LLM applic
 ations in network operations\, currently available as a preprint. Fan&lt;br&gt;i
 s also exploring LLM-driven approaches to automate incident response workf
 lows. Her broader&lt;br&gt;interests include using AI to enhance the infrastruct
 ure and applications of next-generation&lt;br&gt;networks.&lt;/p&gt;\n&lt;p class=&quot;MsoNor
 mal&quot; style=&quot;margin-top: 6.0pt\;&quot;&gt;&amp;nbsp\;&lt;/p&gt;\n&lt;/td&gt;\n&lt;/tr&gt;\n&lt;/tbody&gt;\n&lt;/ta
 ble&gt;
END:VEVENT
END:VCALENDAR