000147165 001__ 147165 000147165 005__ 20250923084434.0 000147165 0247_ $$2doi$$a10.1016/j.plrev.2024.10.013 000147165 0248_ $$2sideral$$a141001 000147165 037__ $$aART-2024-141001 000147165 041__ $$aeng 000147165 100__ $$aLu, Yikang 000147165 245__ $$aLLMs and generative agent-based models for complex systems research 000147165 260__ $$c2024 000147165 5060_ $$aAccess copy available to the general public$$fUnrestricted 000147165 5203_ $$aThe advent of Large Language Models (LLMs) offers to transform research across natural and social sciences, offering new paradigms for understanding complex systems. In particular, Generative Agent-Based Models (GABMs), which integrate LLMs to simulate human behavior, have attracted increasing public attention due to their potential to model complex interactions in a wide range of artificial environments. This paper briefly reviews the disruptive role LLMs are playing in fields such as network science, evolutionary game theory, social dynamics, and epidemic modeling. We assess recent advancements, including the use of LLMs for predicting social behavior, enhancing cooperation in game theory, and modeling disease propagation. The findings demonstrate that LLMs can reproduce human-like behaviors, such as fairness, cooperation, and social norm adherence, while also introducing unique advantages such as cost efficiency, scalability, and ethical simplification. However, the results reveal inconsistencies in their behavior tied to prompt sensitivity, hallucinations and even the model characteristics, pointing to challenges in controlling these AI-driven agents. Despite their potential, the effective integration of LLMs into decision-making processes —whether in government, societal, or individual contexts— requires addressing biases, prompt design challenges, and understanding the dynamics of human-machine interactions. Future research must refine these models, standardize methodologies, and explore the emergence of new cooperative behaviors as LLMs increasingly interact with humans and each other, potentially transforming how decisions are made across various systems. 000147165 536__ $$9info:eu-repo/grantAgreement/ES/DGA/E36-20R$$9info:eu-repo/grantAgreement/ES/MICINN/PID2023-149409NB-I00$$9info:eu-repo/grantAgreement/ES/MICINN/RYC2021-033226-I 000147165 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc$$uhttp://creativecommons.org/licenses/by-nc/3.0/es/ 000147165 590__ $$a14.3$$b2024 000147165 592__ $$a2.384$$b2024 000147165 591__ $$aBIOPHYSICS$$b1 / 79 = 0.013$$c2024$$dQ1$$eT1 000147165 593__ $$aAgricultural and Biological Sciences (miscellaneous)$$c2024$$dQ1 000147165 591__ $$aBIOLOGY$$b1 / 107 = 0.009$$c2024$$dQ1$$eT1 000147165 593__ $$aPhysics and Astronomy (miscellaneous)$$c2024$$dQ1 000147165 593__ $$aArtificial Intelligence$$c2024$$dQ1 000147165 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion 000147165 700__ $$0(orcid)0000-0002-1192-8707$$aAleta, Alberto$$uUniversidad de Zaragoza 000147165 700__ $$aDu, Chunpeng 000147165 700__ $$aShi, Lei 000147165 700__ $$0(orcid)0000-0002-0895-1893$$aMoreno, Yamir$$uUniversidad de Zaragoza 000147165 7102_ $$12004$$2405$$aUniversidad de Zaragoza$$bDpto. Física Teórica$$cÁrea Física Teórica 000147165 773__ $$g51 (2024), 283-293$$pPhysics of Life Reviews$$tPhysics of Life Reviews$$x1571-0645 000147165 8564_ $$s1068259$$uhttps://zaguan.unizar.es/record/147165/files/texto_completo.pdf$$yVersión publicada 000147165 8564_ $$s1735557$$uhttps://zaguan.unizar.es/record/147165/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada 000147165 909CO $$ooai:zaguan.unizar.es:147165$$particulos$$pdriver 000147165 951__ $$a2025-09-22-14:45:30 000147165 980__ $$aARTICLE