LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities

TL;DR

The paper tackles the challenge of integrating large language models (LLMs) into agent-based social simulations to better model complex human behavior. It proposes an organization-oriented multi-agent system (MAS) baseline to structure LLM-augmented ABMs, and outlines seven research directions—literature reviews, modeling architectures, data preparation, datafication, obtaining insights, explainability, and platforms/tools—to guide development. It argues that LLMs can support the entire ABM pipeline, from literature synthesis and data processing to scenario generation and explainable outputs, enabling more nuanced and realistic simulations while highlighting epistemic and ethical risks. The work also situates these ideas within the URBANE Horizon Europe project, underscoring potential practical impacts across social sciences, urban planning, and policy analysis while cautioning against overreliance and misinterpretation of LLM-generated insights.

Abstract

As large language models (LLMs) continue to make significant strides, their better integration into agent-based simulations offers a transformational potential for understanding complex social systems. However, such integration is not trivial and poses numerous challenges. Based on this observation, in this paper, we explore architectures and methods to systematically develop LLM-augmented social simulations and discuss potential research directions in this field. We conclude that integrating LLMs with agent-based simulations offers a powerful toolset for researchers and scientists, allowing for more nuanced, realistic, and comprehensive models of complex systems and human behaviours.