Abstract: Agent-based models (ABMs) are powerful tools for simulating complex systems across various domains, yet their adoption by stakeholders remains limited due to communication challenges. Effective communication of ABMs involves conveying their structure, function, and emergent properties in a way that fosters understanding, trust, and application. A scoping review identifies three major barriers: (1) limited efforts to support ABM reuse, (2) insufficient emphasis on explaining emergent behaviors, and (3) the absence of standardized evaluation methods for communication strategies. To address these challenges, this work explores an automated approach to ABM communication using simulation traces and large language models. By integrating process mining, Business Process Modeling Notation, and narrative generation, this approach transforms raw simulation data into coherent visual and textual artifacts that reflect the model’s dynamic execution. Unlike conventional documentation methods that rely on subjective assessments and require significant modeler effort, this methodology minimizes subjectivity while enhancing accessibility. Demonstrated on a toy model, this approach generates artifacts such as process maps, business process diagrams, and narrative explanations. By mapping current communication strategies and proposing automated tools for execution-based narratives, this work hopes to contribute to the advancement of transparency, stakeholder engagement, and the broader adoption of ABMs.