The paper presents a framework for model selection and parameter estimation using large language models and neural simulation-based inference.

The BEAMS initiative establishes comprehensive benchmarks and evaluates AI tools for modeling and simulation, finding that current AI tools excel at qualitative discussion tasks but struggle with comp…

The paper extends modular dynamic Bayesian networks (MDBNs) to model non-Markovian queues, providing the first causal metamodeling technique for such systems with significant speedup.

A model-driven approach is proposed for generating families of reinforcement learning training environments using a hybrid genetic algorithm and model transformations.

The paper introduces a validation framework to evaluate the realism of LLM-based generative agents in urban simulators against real-world mobility data.

LOTUSim is an open-source, real-time maritime simulator supporting multi-user interaction for coordinated naval-style operations, featuring real-time interactive performance, scalability, and an Ekman…

This paper presents TypoNet, a system that constructs and validates a symbolic model of a production-scale WAN from network artifacts using large language models for translation and a solver for relia…

This paper proposes the trans-domain digital twin approach to connect heterogeneous domain twins through aligned shared state, explicit coupling, heterogeneous temporal coordination, joint decision-ma…

This paper proposes a Model-Based Systems Engineering workflow for creating Digital Twins of Renewable Energy Communities using SysML and the SAREF4ENER ontology.

The paper introduces a genetic algorithm framework to calibrate complex urban traffic simulations using only sparse real-world traffic observations, eliminating the need for detailed employment data.

The paper introduces TaskWeave, a hierarchical agentic framework that successfully simulates long-horizon organizational dynamics by treating coordination as a memory-centered problem, demonstrating t…

This paper explores the integration of Large Language Models as decision-making components in multi-agent simulations for urban mobility modeling.

The paper presents GenWorld, an urban simulation infrastructure for LLM-agent studies, combining a synthetic city, agent-environment interface, and offline compilation of LLM-derived signals.

This paper proposes an automated method to generate complete PDDL planning problems directly from Asset Administration Shell (AAS) capability models, eliminating the need for specialized planning expe…

SimuScene introduces a novel compositional 3D reconstruction pipeline that integrates physics simulation directly into the shape and layout estimation process to generate stable, simulation-ready 3D s…

The paper introduces Battery-Sim-Agent, an LLM-based framework that reframes the difficult inverse problem of battery parameter estimation as a reasoning task, significantly outperforming traditional…

This paper proposes SHA-PF, a search hardness-aware LLM-based problem formulation framework for expensive simulation-driven design, which prioritizes rare samples with greater progress potential and r…

This paper applies the MAP-Elites algorithm to procedurally generate diverse and high-quality First-Person Shooter maps using novel map representations.

The paper advocates for the establishment of Model Science, a systematic discipline that moves beyond simple benchmarking to deeply analyze AI models' internal workings and failure modes.

This paper analyzes the performance and explainability requirements of evolutionary algorithms when applied to complex, real-world physics-informed optimization problems, identifying a gap between cur…