LLMs and Generative Agent-Based Models for Complex Systems

Research Questions

What transformative role do LLMs play in fields such as network science, evolutionary game theory, social dynamics, and epidemic modeling?
How can the Generative Agent-Based Models (GABMs) framework be used to study complex systems?
To what extent can LLM agents imitate human-like social behavior?

LLMs can generate human-like behaviors such as fairness, cooperation, and adherence to social norms.
Responses can show inconsistency due to prompt sensitivity and underlying model biases.
In certain games, LLM agents behaved more cooperatively or more fairly than humans (e.g., Dictator Game, Prisoner’s Dilemma).
Multi-agent systems exhibited emergent social dynamics, including homophily and increased likelihood of repeated interactions.
Multi-agent LLM architectures aligned with human behavior much more closely than single-agent setups (88% vs. 50%).

Human-Like Behavior:
- LLM agents displayed behavior consistent with economic principles such as demand curves and diminishing marginal utility.
Inconsistency and Bias:
- Decisions were influenced even by semantically irrelevant cues such as name or gender.
Rationality Differences:
Compared to humans:
- LLMs behaved more fairly in the Dictator Game.
- LLMs were more cooperative in the Prisoner’s Dilemma (65% vs. human 37%).
Context Effects:
- In epidemic simulations, providing health-related information increased stay-at-home behavior; supplying community-level statistics further reduced social interactions.
Multi-Agent Advantage:
- In the Ultimatum Game, multi-agent LLM systems captured 88% of human behavioral patterns, outperforming single-agent models.
LLM Models: 5
Synthetic Data: 4
Method: 5
Speed: 2
Ethics: 2
Accuracy: 4
Demographics: 2

If you would like to explore this research in more detail, click here to read the full paper.