LLM-Driven Social Influence for Cooperative Behavior in Multi-Agent Systems

This paper presents a novel approach to fostering cooperative behavior in multi-agent systems (MAS) through Large Language Model (LLM)-driven social influence. We propose a theoretical framework where agents’ decision-making processes are influenced not through direct action but by subtle...

Full description

Saved in:
Bibliographic Details
Main Authors: J. de Curto, I. de Zarza
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10912445/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850022891168464896
author J. de Curto
I. de Zarza
author_facet J. de Curto
I. de Zarza
author_sort J. de Curto
collection DOAJ
description This paper presents a novel approach to fostering cooperative behavior in multi-agent systems (MAS) through Large Language Model (LLM)-driven social influence. We propose a theoretical framework where agents&#x2019; decision-making processes are influenced not through direct action but by subtle, narrative-driven influences disseminated by LLMs. These influences guide agents toward cooperative behaviors, such as rural repopulation, without requiring explicit policy interventions. We introduce a formal model grounded in game theory and social network dynamics, where agents balance the direct benefits of action with the indirect payoffs of LLM-guided influence. Using NASH equilibrium and Evolutionarily Stable Strategies (ESS), we demonstrate how cooperative behaviors emerge even when agents remain inactive but are subtly influenced by LLMs. Our experimental simulations validate the model, showing a strong positive correlation between network centrality and influence propagation (<inline-formula> <tex-math notation="LaTeX">$r = 0.969,\; p \lt 0.006$ </tex-math></inline-formula>). Furthermore, temporal analysis reveals that the average influence increases from approximately 0.05&#x2013;0.06 in the initial steps to 0.08&#x2013;0.09 in later stages, indicating a cumulative and self-sustaining trend. In addition, the influence values exhibit a near-normal distribution (Shapiro-Wilk test, <inline-formula> <tex-math notation="LaTeX">$p = 0.285$ </tex-math></inline-formula>) and yield a large effect size (Cohen&#x2019;s <inline-formula> <tex-math notation="LaTeX">$d = 4.530$ </tex-math></inline-formula>) when comparing agents with high versus low network centrality. Through visualization techniques and statistical metrics, we demonstrate the effectiveness of the proposed framework and identify promising directions for future research in AI-driven social influence. This study highlights the potential of LLM-driven narratives as a cost-effective, scalable alternative to traditional policy interventions, offering a new paradigm for promoting societal cooperation in areas such as rural repopulation, sustainability, and community development.
format Article
id doaj-art-a275e36e79fe453ca53d626d836eed61
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-a275e36e79fe453ca53d626d836eed612025-08-20T03:01:31ZengIEEEIEEE Access2169-35362025-01-0113443304434210.1109/ACCESS.2025.354845110912445LLM-Driven Social Influence for Cooperative Behavior in Multi-Agent SystemsJ. de Curto0https://orcid.org/0000-0002-8334-4719I. de Zarza1Department of Computer Applications in Science and Engineering, Barcelona Supercomputing Center, Barcelona, SpainDepartamento de Inform&#x00E1;tica e Ingenier&#x00ED;a de Sistemas, Universidad de Zaragoza, Zaragoza, SpainThis paper presents a novel approach to fostering cooperative behavior in multi-agent systems (MAS) through Large Language Model (LLM)-driven social influence. We propose a theoretical framework where agents&#x2019; decision-making processes are influenced not through direct action but by subtle, narrative-driven influences disseminated by LLMs. These influences guide agents toward cooperative behaviors, such as rural repopulation, without requiring explicit policy interventions. We introduce a formal model grounded in game theory and social network dynamics, where agents balance the direct benefits of action with the indirect payoffs of LLM-guided influence. Using NASH equilibrium and Evolutionarily Stable Strategies (ESS), we demonstrate how cooperative behaviors emerge even when agents remain inactive but are subtly influenced by LLMs. Our experimental simulations validate the model, showing a strong positive correlation between network centrality and influence propagation (<inline-formula> <tex-math notation="LaTeX">$r = 0.969,\; p \lt 0.006$ </tex-math></inline-formula>). Furthermore, temporal analysis reveals that the average influence increases from approximately 0.05&#x2013;0.06 in the initial steps to 0.08&#x2013;0.09 in later stages, indicating a cumulative and self-sustaining trend. In addition, the influence values exhibit a near-normal distribution (Shapiro-Wilk test, <inline-formula> <tex-math notation="LaTeX">$p = 0.285$ </tex-math></inline-formula>) and yield a large effect size (Cohen&#x2019;s <inline-formula> <tex-math notation="LaTeX">$d = 4.530$ </tex-math></inline-formula>) when comparing agents with high versus low network centrality. Through visualization techniques and statistical metrics, we demonstrate the effectiveness of the proposed framework and identify promising directions for future research in AI-driven social influence. This study highlights the potential of LLM-driven narratives as a cost-effective, scalable alternative to traditional policy interventions, offering a new paradigm for promoting societal cooperation in areas such as rural repopulation, sustainability, and community development.https://ieeexplore.ieee.org/document/10912445/Multi-agent systemslarge language modelssocial influencegame theoryNASH equilibriumrural repopulation
spellingShingle J. de Curto
I. de Zarza
LLM-Driven Social Influence for Cooperative Behavior in Multi-Agent Systems
IEEE Access
Multi-agent systems
large language models
social influence
game theory
NASH equilibrium
rural repopulation
title LLM-Driven Social Influence for Cooperative Behavior in Multi-Agent Systems
title_full LLM-Driven Social Influence for Cooperative Behavior in Multi-Agent Systems
title_fullStr LLM-Driven Social Influence for Cooperative Behavior in Multi-Agent Systems
title_full_unstemmed LLM-Driven Social Influence for Cooperative Behavior in Multi-Agent Systems
title_short LLM-Driven Social Influence for Cooperative Behavior in Multi-Agent Systems
title_sort llm driven social influence for cooperative behavior in multi agent systems
topic Multi-agent systems
large language models
social influence
game theory
NASH equilibrium
rural repopulation
url https://ieeexplore.ieee.org/document/10912445/
work_keys_str_mv AT jdecurto llmdrivensocialinfluenceforcooperativebehaviorinmultiagentsystems
AT idezarza llmdrivensocialinfluenceforcooperativebehaviorinmultiagentsystems