AI RESEARCH
Specification-Driven Generation and Evaluation of Discrete-Event World Models via the DEVS Formalism
arXiv CS.AI
•
ArXi:2603.03784v2 Announce Type: replace World models are central to LLM agents that must evaluate actions over long horizons. Yet much existing work focuses on environments governed by physical dynamics or spatial structure, whereas many high-impact domains, including supply chains, procurement networks, and business processes, evolve through discrete events, timing constraints, and causal dependencies. These settings call for discrete-event world models.