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...
Saved in:
| Main Authors: | , |
|---|---|
| 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’ 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 0.05–0.06 in the initial steps to 0.08–0.09 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’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 Informática e Ingeniería 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’ 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 0.05–0.06 in the initial steps to 0.08–0.09 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’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 |