BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//hacksw/handcal//NONSGML v1.0//EN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260520T230016Z
DESCRIPTION:Click for Latest Location Information: http://dgiq-edw2026.data
 versity.net/sessionPop.cfm?confid=165&proposalid=16423\nAs AI systems evolv
 e from passive models to autonomous agents, a central challenge is enabling
  them to understand and interact with the world. Agentic AI requires more t
 han predictive accuracy—agents must interpret environments, reason un
 der uncertainty, plan multi-step actions, and operate responsibly. This tut
 orial introduces modeling disciplines that make these capabilities possible
 : environment modeling, semantic modeling, behavior modeling, and risk mode
 ling. These techniques form the cognitive structure for agents to behave sa
 fely, predictively, and effectively.\n\nWe will explore several modeling&nb
 sp;techniques, including state transition, causal loop, ontology, knowledge
  graph, action schemas, memory systems, reward structures, and safety const
 raints. The focus here is on why modeling matters: autonomous systems behav
 e only as well as their internal understanding of the world.\n\nBy the end 
 of the session, you will understand the modeling foundations needed to buil
 d reliable agentic AI systems and be prepared to evaluate and improve agent
  design. You will learn how to:\n\n
 Model environments using structural, dynamic, and interaction-oriented tech
 niques\n	Build semantic and data models that ground agent understanding\n
 Model for memory architectures that support context, retrieval, and continu
 ity\n
 Apply reasoning, decision, and planning models to guide autonomous behavior
 \n
 Model risks, constraints, and failure modes to ensure safe agent behavior\n
 Integrate models into coherent and cohesive agent design\n\n
DTSTART:20260504T134500
SUMMARY:T16: Modeling Techniques for Agentic AI
DTEND:20260504T165959
LOCATION: See Description
END:VEVENT
END:VCALENDAR