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

arXiv: https://arxiv.org/abs/2603.03784 · HTML: https://mlsanity.com/paper/2603.03784/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 21 of 21)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [DayDreamer: World Models for Physical Robot Learning](https://mlsanity.com/paper/2206.14176/) (2022)
- [RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems](https://mlsanity.com/paper/2306.03091/) (2023)
- [Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents](https://mlsanity.com/paper/2411.06559/) (2024)
- [Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation](https://mlsanity.com/paper/2410.13232/) (2024)
- [Language Models Meet World Models: Embodied Experiences Enhance Language Models](https://mlsanity.com/paper/2305.10626/) (2023)
- [Metamorphic Testing: A New Approach for Generating Next Test Cases](https://mlsanity.com/paper/2002.12543/) (2020)
- [NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents](https://mlsanity.com/paper/2512.12730/) (2025)
- [FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation](https://mlsanity.com/paper/2503.06680/) (2025)
- [From Word to World: Can Large Language Models be Implicit Text-based World Models?](https://mlsanity.com/paper/2512.18832/) (2025)
- [PWM: Policy Learning with Multi-Task World Models](https://mlsanity.com/paper/2407.02466/) (2024)
- [Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models](https://mlsanity.com/paper/2407.12979/) (2024)
- [PROC2PDDL: Open-Domain Planning Representations from Texts](https://mlsanity.com/paper/2403.00092/) (2024)
- [Evaluating Large Language Models on Business Process Modeling: Framework, Benchmark, and Self-Improvement Analysis](https://mlsanity.com/paper/2412.00023/) (2024)
- [Web World Models](https://mlsanity.com/paper/2512.23676/) (2025)
- [A System Model Generation Benchmark from Natural Language Requirements](https://mlsanity.com/paper/2508.03215/) (2025)
- [Scalable, Symbiotic, AI and Non-AI Agent Based Parallel Discrete Event Simulations](https://mlsanity.com/paper/2505.23846/) (2025)

## Built on by (most cited first, 1 of 1)

- [LLM-Guided Heuristic Design from Simulation Traces: A Case Study in Dynamic Production and AGV Scheduling](https://mlsanity.com/paper/2608.09343/) (2026)

## Abstract (arXiv)

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. Existing approaches to constructing world models often fall near two extremes: hand-engineered simulators provide consistency and reproducibility, but are costly to build and adapt; neural models are flexible, but can suffer from compounding inconsistency over long-horizon rollouts. We seek a principled middle ground by synthesizing discrete-event world models online from natural-language specifications, retaining the reliability of explicit simulators while gaining the adaptability of neural models. We adopt the DEVS formalism and introduce a staged LLM-based generation pipeline that separates structural inference over component interactions from component-level event and timing logic. For evaluation, we develop benchmark suites in which simulators emit structured event traces, which are then validated against specification-derived temporal, causal, and semantic constraints. This enables reproducible verification and localized diagnostics. Together, these contributions produce world models that remain consistent over long-horizon rollouts, can be verified from observable behavior, and can be synthesized efficiently on demand during online execution.