Specification-Driven Generation and Evaluation of Discrete-Event World Models via the DEVS Formalism

TL;DR

This work adopts the DEVS formalism and introduces a staged LLM-based generation pipeline that separates structural inference of component interactions from component-level event and timing logic, and produces world models that are consistent over long-horizon rollouts, verifiable from observable behavior, and efficient to synthesize on demand during online execution.

Abstract

World models are essential for planning and evaluation in agentic systems, yet existing approaches lie at two extremes: hand-engineered simulators that offer consistency and reproducibility but are costly to adapt, and implicit neural models that are flexible but difficult to constrain, verify, and debug over long horizons. We seek a principled middle ground that combines the reliability of explicit simulators with the flexibility of learned models, allowing world models to be adapted during online execution. By targeting a broad class of environments whose dynamics are governed by the ordering, timing, and causality of discrete events, such as queueing and service operations, embodied task planning, and message-mediated multi-agent coordination, we advocate explicit, executable discrete-event world models synthesized directly from natural-language specifications. Our approach adopts the DEVS formalism and introduces a staged LLM-based generation pipeline that separates structural inference of component interactions from component-level event and timing logic. To evaluate generated models without a unique ground truth, simulators emit structured event traces that are validated against specification-derived temporal and semantic constraints, enabling reproducible verification and localized diagnostics. Together, these contributions produce world models that are consistent over long-horizon rollouts, verifiable from observable behavior, and efficient to synthesize on demand during online execution.

Figures (5)

• Figure 1: Illustrative example of the generation and execution of a discrete-event world model for a warehouse robot fleet restocking task. To facilitate planning, a natural-language environment specification is translated into a world model, which exposes a standardized execution interface for interventions (e.g., fleet size, dispatching rule, charger count) and emits a structured event trace and performance metrics (e.g., KPIs). In this paper, we propose to operationalize such a world model as a DEVS model composed of interacting atomic and coupled components, each representing an entity with local state, event-handling logic, and timing semantics. Interactions among entities are realized through event messages routed via component ports, while event timing is governed by component-specific time-advance and transition functions. This enables systematic what-if analysis and comparative evaluation of alternative operational policies.
• Figure 2: Generation pipeline of the discrete-event world model for warehouse robot fleet restocking.
• Figure 3: Ablation study on synthesis latency (using GPT-5.2). The chart compares the wall-clock time required for the Planning and Generation phases under serial and parallel execution modes. While the acceleration in the Planning phase is limited by the current benchmark scale, the Generation phase achieves a $4.7\times$ speedup, validating the scalability of the approach.
• Figure 4: Visualized PlanTree hierarchy for the ABP Model. The root model recursively decomposes into sub-models until atomic primitives are reached.
• Figure 5: The final connection of the ABP DEVS model.