BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Sabre//Sabre VObject 4.5.8//EN
CALSCALE:GREGORIAN
LAST-MODIFIED:20250721T082807Z
BEGIN:VTIMEZONE
TZID:Europe/Zurich
BEGIN:STANDARD
DTSTART:20241027T010000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:STANDARD
DTSTART:20251026T010000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20250330T010000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:5a77b997-467b-4d5d-bb40-b84789c17d2e
DTSTAMP:20250721T082807Z
SUMMARY:W3C WebAgents CG: Biweekly Call (Fridays)
DTSTART;TZID=Europe/Zurich:20250801T101500
DTEND;TZID=Europe/Zurich:20250801T111500
DESCRIPTION:https://www.w3.org/events/meetings/5a77b997-467b-4d5d-bb40-b847
 89c17d2e/20250801T090000/\n\nBiweekly call of the W3C Autonomous Agents on
  the Web (WebAgents) Community Group.\n\nFor more information about regula
 r meetings\, see the [group's wiki](https://github.com/w3c-cg/webagents/wi
 ki/Regular-CG-Meetings).\n\nAgenda: https://github.com/w3c-cg/webagents/wi
 ki/Regular-CG-Meetings\n\nAgenda\n\n**Amit Chopra — Why Agentic AI Needs
  Interaction-Oriented Programming**\n\n**Abstract:** Agentic AI envisages 
 the use of Generative AI\, especially LLMs\, as a decision-making engine f
 or agents. Its value arises from the ability to reason flexibly in a varie
 ty of contexts but without explicit knowledge engineering.  Exploiting thi
 s flexibility requires approaches for modeling multiagent interactions tha
 t support flexibility. Workflow\, the currently dominant paradigm for mode
 ling interactions in Agentic\, doesn't fit the bill\; it hasn't since the 
 1990s.\n\nThe multiagent systems community took an alternative approach: W
 ith of aim of supporting intelligent decision making by agents\, they soug
 ht to capture the meaning of interactions. KQML and the FIPA ACL were earl
 y missteps. Interaction-Oriented Programming (IOP) addresses these misstep
 s.  IOP is formal\, declarative\, and general purpose (can be used to mode
 l diverse applications). It is motivated from meaning and supports maximal
 ly flexible interactions between agents. No approach supports loose-coupli
 ng\, including asynchrony and heterogeneity\, better than IOP. Moreover\, 
 IOP boasts a growing repository of software\, including compilers\, verifi
 ers\, and programming models (https://gitlab.com/masr).\n\nIn this talk\, 
 I will touch upon the past\, the present\, and the future of multiagent in
 teractions\, as relevant to Agentic AI. Let us not repeat the mistakes of 
 the past.\n\n**Biography:** Amit K. Chopra is a senior lecturer at Lancast
 er University in the UK. He is interested in software abstractions that en
 able engineering flexible\, decentralized multiagent systems. The notions 
 of protocols and norms are central to this work\, which has been published
  in prestigious AI conferences such as AAMAS\, IJCAI\, and AAAI.  \n\nAmit
  has given several tutorials and invited talks. His research has been fund
 ed by the UKRI and the EU.  He has a PhD in Computer Science from North Ca
 rolina State University.
STATUS:CONFIRMED
CREATED:20250205T202251Z
LAST-MODIFIED:20250721T082807Z
SEQUENCE:1
ORGANIZER;CN=W3C Calendar;PARTSTAT=ACCEPTED;ROLE=NON-PARTICIPANT:mailto:nor
 eply@w3.org
ATTENDEE;CUTYPE=GROUP;ROLE=OPT-PARTICIPANT;RSVP=FALSE;CN=Autonomous Agents 
 on the Web Community Group:mailto:public-webagents@w3.org
RECURRENCE-ID;TZID=Europe/Zurich:20250801T090000
END:VEVENT
END:VCALENDAR