Integrating LLM in Agent-Based Social Simulation: Opportunities and Challenges
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918359810965504 |
|---|---|
| author | Taillandier, Patrick Zucker, Jean Daniel Grignard, Arnaud Gaudou, Benoit Huynh, Nghi Quang Drogoul, Alexis |
| author_facet | Taillandier, Patrick Zucker, Jean Daniel Grignard, Arnaud Gaudou, Benoit Huynh, Nghi Quang Drogoul, Alexis |
| contents | This position paper examines the use of Large Language Models (LLMs) in social simulation, analyzing their potential and limitations from a computational social science perspective. We first review recent findings on LLMs' ability to replicate key aspects of human cognition, including Theory of Mind reasoning and social inference, while identifying persistent limitations such as cognitive biases, lack of grounded understanding, and behavioral inconsistencies. We then survey emerging applications of LLMs in multi-agent simulation frameworks, examining system architectures, scalability, and validation strategies. Projects such as Generative Agents (Smallville) and AgentSociety are analyzed with respect to their empirical grounding and methodological design. Particular attention is given to the challenges of behavioral fidelity, calibration, and reproducibility in large-scale LLM-driven simulations. Finally, we distinguish between contexts where LLM-based agents provide operational value-such as interactive simulations and serious games-and contexts where their use raises epistemic concerns, particularly in explanatory or predictive modeling. We argue that hybrid approaches integrating LLMs into established agent-based modeling platforms such as GAMA and NetLogo may offer a promising compromise between expressive flexibility and analytical transparency. Building on this analysis, we outline a conceptual research direction termed Hybrid Constitutional Architectures, which proposes a stratified integration of classical agent-based models (ABMs), small language models (SLMs), and LLMs within established platforms such as GAMA and NetLogo. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19364 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Integrating LLM in Agent-Based Social Simulation: Opportunities and Challenges Taillandier, Patrick Zucker, Jean Daniel Grignard, Arnaud Gaudou, Benoit Huynh, Nghi Quang Drogoul, Alexis Artificial Intelligence Multiagent Systems This position paper examines the use of Large Language Models (LLMs) in social simulation, analyzing their potential and limitations from a computational social science perspective. We first review recent findings on LLMs' ability to replicate key aspects of human cognition, including Theory of Mind reasoning and social inference, while identifying persistent limitations such as cognitive biases, lack of grounded understanding, and behavioral inconsistencies. We then survey emerging applications of LLMs in multi-agent simulation frameworks, examining system architectures, scalability, and validation strategies. Projects such as Generative Agents (Smallville) and AgentSociety are analyzed with respect to their empirical grounding and methodological design. Particular attention is given to the challenges of behavioral fidelity, calibration, and reproducibility in large-scale LLM-driven simulations. Finally, we distinguish between contexts where LLM-based agents provide operational value-such as interactive simulations and serious games-and contexts where their use raises epistemic concerns, particularly in explanatory or predictive modeling. We argue that hybrid approaches integrating LLMs into established agent-based modeling platforms such as GAMA and NetLogo may offer a promising compromise between expressive flexibility and analytical transparency. Building on this analysis, we outline a conceptual research direction termed Hybrid Constitutional Architectures, which proposes a stratified integration of classical agent-based models (ABMs), small language models (SLMs), and LLMs within established platforms such as GAMA and NetLogo. |
| title | Integrating LLM in Agent-Based Social Simulation: Opportunities and Challenges |
| topic | Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2507.19364 |