Innovations in Multi-Agent Systems: LLMs, Social Simulation, and Disinformation Dynamics

Dear Colleagues,

This Special Issue aims to explore the transformative impact of integrating Large Language Models (LLMs) into Multi-Agent Systems (MAS), with a specific focus on applications in the social sciences. As AI agents become capable of autonomous reasoning and complex social interaction, they offer unprecedented opportunities for modeling human behavior, societal dynamics, and information flow. The transition from single-agent LLMs to orchestrated Multi-Agent Systems allows for the simulation of intricate socio-cognitive environments.

When applied to social simulation, generative agents can mimic information diffusion, relationship building, and societal consensus. However, this same capability introduces critical avenues for studying digital threats. A key area of interest is the simulation and mitigation of these threats, including the propagation of propaganda and disinformation across both simulated environments and real-world social networks. By prioritizing applications in social research, this collection will provide vital insights into emergent human-like behaviors and the growing necessity of understanding disinformation spread in modern digital ecosystems.

We invite contributions that advance conceptual frameworks or present practical applications of social research. This Special Issue gathers cutting-edge research on how LLM-driven agents coordinate, form social structures, and diffuse information. Submissions are welcome on LLM-driven social simulation and computational sociology , including studies on the diffusion of propaganda and disinformation within artificial agent networks. Research on emergent group dynamics, artificial culture, and polarization is highly relevant. We also seek papers on agentic coordination, consensus building, and the application of MAS to public policy and social intervention modeling.

Topics of Interest

Topics of interest include, but are not limited to, conceptually driven or empirically based research across the following four areas:

• Foundations of LLM-Driven Social Agents: Conceptual developments in agentic architectures. We welcome papers exploring the underlying mechanisms by which large language models facilitate memory, opinions, individual reasoning, and complex social cognition. This includes how autonomous entities negotiate, resolve conflicts, and reach agreements in complex social or economic environments.
• Emergent Dynamics in Artificial Societies: Computational sociology, cultural evolution, and the formation of echo chambers. Contributions should explore how artificial agents organically form relationships and communities over time. LLM-based social simulation is rapidly growing as researchers use agents to mimic entire communities to test sociological and psychological hypotheses in digital sandboxes.
• Modeling Propaganda and Disinformation Networks: Simulating the diffusion of fake news and malicious narratives through real social networks or multi-agent ecosystems. We encourage papers that propose automated monitoring and interventions to detect and counter digital manipulation. We also welcome papers seeking new ways to measure the social impact of propaganda and disinformation.
• Applications in Social Policy and Intervention: Practical social research in which advanced systems are used to predict demographic responses to public regulations or test socioeconomic theories.

References

• Abdelnabi, S., Gomaa, A., Sivaprasad, S., Schönherr, L., & Fritz, M. (2024). Cooperation, competition, and maliciousness: Llm-stakeholders interactive negotiation. Advances in Neural Information Processing Systems, 37, 83548-83599.
• Farr, D., Ng, L. H. X., Prochaska, S., Cruickshank, I. J., & West, J. (2025). Simulating misinformation vulnerabilities with agent personas. In 2025 Winter Simulation Conference (pp. 1907-1918). IEEE.
• Gao, C., Lan, X., Lu, Z., Mao, J., Piao, J., Wang, H., ... & Li, Y. (2023). S3: Social-network simulation system with large language model-empowered agents. arXiv preprint arXiv:2307.14984.
• Papageorgiou, E., Chronis, C., Varlamis, I., & Himeur, Y. (2024). A survey on the use of large language models (LLMs) in fake news. Future Internet, 16(8), 298.
• Park, J. S., O'Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023). Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (pp. 1–22).
• Roumeliotis, K. I., Tselikas, N. D., & Nasiopoulos, D. K. (2025). Fake news detection and classification: A comparative study of convolutional neural networks, large language models, and natural language processing models. Future Internet, 17(1), 28.
• Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., ... & Wen, J. R. (2024). A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6), 186345.

Prof. Dr. Darius Plikynas
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Systems is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• multi-agent systems
• agent-based models
• large language models
• social simulation
• generative agents
• disinformation and propaganda
• emergent behavior