Universidad de Zaragoza Repository

000151326 001__ 151326
000151326 005__ 20251017144622.0
000151326 0247_ $$2doi$$a10.1109/ACCESS.2025.3548451
000151326 0248_ $$2sideral$$a143136
000151326 037__ $$aART-2025-143136
000151326 041__ $$aeng
000151326 100__ $$ade Curtò, J.
000151326 245__ $$aLLM-Driven Social Influence for Cooperative Behavior in Multi-Agent Systems
000151326 260__ $$c2025
000151326 5060_ $$aAccess copy available to the general public$$fUnrestricted
000151326 5203_ $$aThis 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, narrativedriven 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 (r = 0.969, p < 0.006). 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, p = 0.285) and yield a large effect size (Cohen’s d = 4.530) 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.
000151326 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es
000151326 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000151326 700__ $$0(orcid)0000-0002-5844-7871$$ade Zarzà, I.$$uUniversidad de Zaragoza
000151326 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf.
000151326 773__ $$g13 (2025), [13 pp.]$$pIEEE Access$$tIEEE Access$$x2169-3536
000151326 8564_ $$s2704091$$uhttps://zaguan.unizar.es/record/151326/files/texto_completo.pdf$$yVersión publicada
000151326 8564_ $$s2719707$$uhttps://zaguan.unizar.es/record/151326/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000151326 909CO $$ooai:zaguan.unizar.es:151326$$particulos$$pdriver
000151326 951__ $$a2025-10-17-14:22:14
000151326 980__ $$aARTICLE

The server encountered an error while dealing with your request.

The system administrators have been alerted.

In case of doubt, please contact deposita@unizar.es.