NetworkGames: Simulating Cooperation in Network Games with Personality-driven LLM Agents

📅 2025-11-26
📈 Citations: 0
Influential: 0
📄 PDF

career value

216K/year
🤖 AI Summary
Understanding how network topology and agent personality traits jointly shape the evolution of cooperation remains an open challenge. Method: We propose the first networked game simulation framework integrating MBTI-based personality modeling with large language model (LLM)-driven agents, enabling personality-informed behavioral simulation; we conduct repeated Prisoner’s Dilemma multi-agent simulations on small-world and scale-free networks. Contribution/Results: We demonstrate that cooperation evolution cannot be predicted solely from pairwise interactions but emerges from the coupling between personality spatial distribution and network structure. Specifically, cooperation levels significantly increase when prosocial personalities concentrate at hub nodes in scale-free networks, whereas small-world topologies consistently suppress cooperation. To support reproducible research, we open-source the NetworkGames simulation framework—a novel methodological foundation for investigating personality–structure coevolutionary effects in complex adaptive systems.

Technology Category

Application Category

📝 Abstract
The advent of Large Language Models (LLMs) presents a novel opportunity to build high-fidelity agent-based models for simulating complex social systems. However, the behavior of these LLM-based agents in game-theoretic network games remains surprisingly unexplored. In this work, we introduce "NetworkGames," a novel simulation framework designed to investigate how network topology and agent personality jointly shape the evolution of cooperation in network games. We instantiate a population of LLM agents, each endowed with a distinct personality from the MBTI taxonomy, and situate them in various network structures (e.g., small-world and scale-free). Through extensive simulations of the Iterated Prisoner's Dilemma, we first establish a baseline dyadic interaction matrix, revealing nuanced cooperative preferences between all 16 personality pairs. We then demonstrate that macro-level cooperative outcomes are not predictable from dyadic interactions alone; they are co-determined by the network's connectivity and the spatial distribution of personalities. For instance, we find that small-world networks are detrimental to cooperation, while strategically placing pro-social personalities in hub positions within scale-free networks can significantly promote cooperative behavior. Our findings offer significant implications for designing healthier online social environments and forecasting collective behavior. We open-source our framework to foster further research in network game simulations.
Problem

Research questions and friction points this paper is trying to address.

Investigates how network structure and personality affect cooperation evolution in games
Explores LLM agents' behavior in network games using MBTI personality types
Examines macro cooperation outcomes shaped by network connectivity and personality distribution
Innovation

Methods, ideas, or system contributions that make the work stand out.

LLM agents with MBTI personalities simulate network games
Framework analyzes cooperation via network topology and personality distribution
Small-world networks hinder cooperation, scale-free hubs boost it