BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.2//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:Eventi DIAG
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:STANDARD
DTSTART:20261025T030000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T020000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RDATE:20270328T020000
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.31457.field_data.0@www.diag.uniroma1.it
DTSTAMP:20260916T192714Z
CREATED:20260915T085654Z
DESCRIPTION:Speaker: Leonardo Ranaldi (University of Rome Tor Vergata)Title
 : Adaptive Reasoning Agents - The Extent to Which Agents Should AdaptAbstr
 act: Automated agents powered by LLMs are moving from answering questions 
 to reasoning\, deciding\, and acting. Longer\, more complex interactions m
 ake adaptation part of the reasoning process\, where answers are revised\,
  procedures modified\, experience retained\, and previous interactions use
 d to steer later decisions.The central question is how an agent learns wha
 t to change\, and how experience can lead that decision.This seminar treat
 s adaptation as a reasoning problem. Effective adaptation requires represe
 nting what is changing\, evaluating evidence for change\, and anticipating
  consequences. The discussion centres on four capacities: representing a p
 roblem\, revising a stance\, consolidating experience into reusable proced
 ures\, and anticipating an action's effects. Across these capabilities\, q
 uasi-symbolic abstractions deliver a proper structure for examining\, revi
 sing\, and reusing them while preserving the flexibility of natural langua
 ge. The seminar closes by looking ahead to how single-agent learning can e
 volve collective practice for a group.Bio: Leonardo Ranaldi did his PhD at
  the University of Rome Tor Vergata\, where he is a member of the academic
  staff. After a postdoc at the Idiap Research Institute\, he joined the Un
 iversity of Edinburgh as a Research Fellow. His research focuses on adapti
 ve reasoning\, agent memory\, and controllable generation\, with particula
 r interest in how AI systems learn from interaction and reuse experience o
 ver time. He works across international research collaborations and regula
 rly organises workshops at major CL/NLP venues. Zoom link: https://uniroma
 1.zoom.us/j/85485829872?pwd=DVnUcL3bP6PammzbKe4htvWabslRw5.1  
DTSTART;TZID=Europe/Paris:20260918T113000
DTEND;TZID=Europe/Paris:20260918T113000
LAST-MODIFIED:20260915T145608Z
LOCATION:Zoom link: https://uniroma1.zoom.us/j/85485829872?pwd=DVnUcL3bP6Pa
 mmzbKe4htvWabslRw5.1
SUMMARY:Seminari di Ingegneria Informatica - Leonardo Ranaldi: Adaptive Rea
 soning Agents - The Extent to Which Agents Should Adapt - Leonardo Ranaldi
URL;TYPE=URI:https://www.diag.uniroma1.it/node/31457
END:VEVENT
END:VCALENDAR