Social Simulations: from Agent-Based Modeling to Digital Twins

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Erica Cau, Andrea Failla, Valentina Pansanella, Giulio Rossetti
• Venue: arXiv: cs.MA
• Published: 2026-07-15
• Collected: 2026-07-16
• URL: http://arxiv.org/abs/2607.13693v1
• PDF: https://arxiv.org/pdf/2607.13693v1
• DOI: UNKNOWN

Plain-Language Brief

The text discusses the evolution of social simulation, moving from traditional agent-based models with explicitly defined rules to more advanced simulations using Large Language Models and Social Digital Twins. It highlights the methodological foundations, applications, advantages, and limitations of each paradigm.

What the Document Says

• The text covers the evolution of social simulation from classical agent-based models to AI-enhanced simulations and Social Digital Twins.
• Agent-based models have explicitly defined behavioral rules for agents.

Key Concepts Mentioned

• social simulation
• agent-based modeling
• Large Language Models
• Social Digital Twins

Claims Made by the Document

• There is a progression from abstract models investigating general social mechanisms to more realistic computational representations of specific social systems.

Evidence Used

• The text mentions the evolution and shift in methodologies for social simulation.

Methods / Approach

• Discussion and comparison of various paradigms in social simulation.

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

• The text may lack specific details about the implementation or practical aspects of these simulations.
• The text does not provide examples of actual simulations or their outcomes.

Open Questions

• What are some concrete examples of AI-enhanced simulations and Social Digital Twins?
• How effective are these advanced simulations in accurately representing real-world socio-technical systems?

Notes for Future Q&A

May include interpretation. Labeled where it does.

• The text focuses on the evolution and methodologies rather than providing practical examples or outcomes.
• The authors discuss advances in social simulation, but do not provide specific details about their own work.

Raw Abstract / Excerpt

This book chapter covers the evolution of social simulation from classical agent-based models, in which agents interact according to explicitly defined behavioral rules, to AI-enhanced simulations based on Large Language Models and, ultimately, Social Digital Twins: high-fidelity, data-driven representations of real-world socio-technical systems. Along this trajectory, we discuss the main methodological foundations, applications, advantages, and limitations of each paradigm, highlighting the progressive shift from abstract models designed to investigate general social mechanisms toward increasingly realistic computational representations of specific social systems.