S3: Social-network Simulation System with Large Language Model-Empowered Agents
Open accessThe DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Abstract
Simulation plays a crucial role in addressing various challenges within social science. It offers extensive applications such as state prediction, phenomena explanation, and policy-making support, among others. In this work, we harness the human-like capabilities of large language models (LLMs) in sensing, reasoning, and behaving, and utilize these qualities to construct the S3 system (short for Social network Simulation System). Adhering to the widely employed agent-based simulation paradigm, we employ fine-tuning and prompt engineering techniques to ensure that the agent's behavior closely emulates that of a genuine human within the social network. Specifically, we simulate three pivotal aspects: emotion, attitude, and interaction behaviors. By endowing the agent in the system with the ability to perceive the informational environment and emulate human actions, we observe the emergence of population-level phenomena, including the propagation of information, attitudes, and emotions. We conduct an evaluation encompassing two levels of simulation, employing real-world social network data. Encouragingly, the results demonstrate promising accuracy. This work represents an initial step in the realm of social network simulation empowered by LLM-based agents. We anticipate that our endeavors will serve as a source of inspiration for the development of simulation systems within, but not limited to, social science.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“LLM-driven populations display spontaneous emergent behaviours akin to human societies, such as scale-free networks [26], information diffusion [27], and social conventions through interactions [28].”
From Selective agreement, not sycophancy: investigating opinion dynamics in LLM interactions (2025) · cites this paper as [27]
In the citing paper
“Similarly, Gao et al. use real-world social media data to calibrate a model they claim successfully predicts the spread of information and emotions about gender discrimination and nuclear energy (40).”
From Can Generative AI improve social science? (2024) · cites this paper as [40]
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Kaugeranna, R., Kaugeranna, E., & Aion, (. S. 4. 6. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.giscience.2023.43 · Cited by 13,690
Status quo bias in decision making
Samuelson, W., & Zeckhauser, R. (1988) · Journal of Risk and Uncertainty · doi:10.1007/bf00055564 · Cited by 5,897
Understanding Social Preferences with Simple Tests
Charness, G., & Rabin, M. (2002) · The Quarterly Journal of Economics · doi:10.1162/003355302760193904 · Cited by 3,970
Simulation for the Social Scientist
Gilbert, N., & Troitzsch, K. G. (1999) · Cited by 2,352
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606763 · Cited by 2,187
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · arXiv · doi:10.48550/arxiv.2304.03442 · Cited by 2,173
Bratley, P., Fox, B. L., & Schrage, L. E. (1987) · Springer eBooks · doi:10.1007/978-1-4419-8724-2 · Cited by 1,468
Lee, L.-H., Braud, T., Zhou, P., Wang, L., Xu, D., Lin, Z., Kumar, A., Bermejo, C., & Hui, P. (2021) · arXiv · doi:10.48550/arxiv.2110.05352 · Cited by 1,088
Lee, L.-H., Braud, T., Zhou, P. Y., Wang, L., Xu, D., Lin, Z., Kumar, A., Bermejo, C., & Hui, P. (2024) · Foundations and Trends® in Human-Computer Interaction · doi:10.1561/1100000095 · Cited by 1,082
Research works printed but not linked: 6
- Bastien Chopard, 1998, Cellular automata. Modelling of Physical, 6
- Aakanksha Chowdhery, 2022, Scaling language modeling with pathways
- Rohan Anil, 2023, Palm 2 technical report
- C Lawrence, 1978, Using system dynamics to model the social security system, NBER Workshop on Policy Analysis with Social Security Research Files, 15
- 2023, OpenAI. Gpt-4 technical report
- Hugo Touvron, 2023, Open and efficient foundation language models
Cited by
Items 101–120 of 120
PoliSim@CHI 2026: LLM Agent Simulation for Policy
Li, Y., Deng, W. H., Zhou, X., Klyman, K., Yu, C., Shi, Y., Vincent, N., Zhang, A. X., Sap, M., Das, S., et al. (2026) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3772363.3778738
Self-citationLi, J., Jiang, J., Tang, S., Yu, M., Song, X., Xue, C., Su, Y., Tan, X., & Shi, Y. (2026) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791543 · Cited by 1
Bian, C., Zhai, Z., Ye, S., & Lu, W. (2026) · IEEE Transactions on Learning Technologies · doi:10.1109/tlt.2026.3692781
How Humans and LLMs Differ in Processing Uncertainty in Polarized Discourse
Donkers, T., & Ziegler, J. (2026) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3774935.3806174
Large language model-based multi-agent systems for financial markets simulation: a survey
Liu, Q., Yao, L., Wang, Z., Yang, Y., Tang, Y. J., Cheng, D., & Jiang, C. (2026) · Science China Information Sciences · doi:10.1007/s11432-026-4986-x · Cited by 3
YSocial: An artificial intelligence powered social media virtual twin
Rossetti, G., Stella, M., Cazabet, R., Abramski, K., Citraro, S., Cau, E., Failla, A., Morini, V., & Pansanella, V. (2026) · Big Data & Society · doi:10.1177/20539517261431576 · Cited by 4
A Comparative Survey of Security Risks in AI Systems: From LLMs to AI Agents and Embodied Agents
Wu, B., Li, Q., Zhou, C., Wang, T., & Ji, S. (2026) · ACM Computing Surveys · doi:10.1145/3837083 · Cited by 3
Song, J., Xia, Y., Kong, B., Cheng, L., Zhuo, C., Zang, L., & Yu, C. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818421
Reinforcement Learning in the Era of Large Language Models: Challenges and Opportunities
Hao, Q., Chen, L., Qi, X.-K., Yuan, Y., Zong, Z., Chen, H. S., Zhao, K., Wang, S., Zhang, Y., Yuan, J., et al. (2026) · ACM Computing Surveys · doi:10.1145/3837057
Self-citationLLM-Based User Simulation as a Tool for Investigating Complex Socio-Technical Applications
Donkers, T., & Ziegler, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-22937-3_6
Cardozo, J. I. L. (2026) · De Gruyter eBooks · doi:10.1515/9783112237687-002
Complexity-Driven Agent Routing for Scalable Opinion Dynamic Simulation
Yu, Q., Zhou, D., Wang, X., & Zhu, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38410-2_38
Chang, X., Tao, S., Kawai, M., & Takizawa, H. (2026) · International Conference on Computational Intelligence and Machine Learning (CIML) · doi:10.1109/ciml69155.2026.11692797
Artificial intelligence-enabled e-services for justice system services delivery in Namibia
Mendonca, H., Iyamu, T., & Idemudia, E. C. (2026) · South African journal of information management · doi:10.4102/sajim.v28i1.2171
Characterizing an LLM-driven Social Network: The Case of Chirper.ai
Zhu, Y., He, Y., Haq, E.-U., Tyson, G., & Hui, P. (2026) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3816910 · Cited by 23
PsyAgentRec: Psychology-Grounded Agents for Adaptive Recommendation
Zhong, H., & Zhu, S. (2026) · International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence (ISMSI) · doi:10.1145/3820820.3820821
From Interaction Topology to Realized Context: Diagnosing Exposure in LLM-Agent Social Simulation
Xu, Y., Han, X., & Ma, C. (2026) · ACM Turing Celebration Conference - China (ACM TURC) · doi:10.1145/3833142.3833202
AI-generated language remains systematically distinguishable from human communication
Pagan, N., Törnberg, P., Bail, C. A., & Barrie, C. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2531748123 · Cited by 10
Mikhailova, S. S., Danilova, S. V., & Timofeev, A. N. (2026) · Vestnik NSUEM · doi:10.34020/2073-6495-2026-3-031-045
Lyfe Agents: Generative agents for low-cost real-time social interactions
Kaiya, Z., Naim, M., Kondic, J., Cortes, M., Ge, J., Luo, S., Yang, G. R., & Ahn, A. (2023) · arXiv · doi:10.48550/arxiv.2310.02172 · Cited by 2
Metadata
- Authors
- Gao, C., Lan, X., Lu, Z., Mao, J., Piao, J., Wang, H., Jin, D., & Li, Y.
- Affiliations
- Tsinghua University (CN)
- Corresponding author
- Gao, Chen
- Venue
- SSRN Electronic Journal
- Publisher
- Elsevier BV
- Published
- 2023
- ISSN
- 1556-5068 (ISSN-L)
- OpenAlex
- W4388744821
- Cited by
- 113
- References
- 34
- Citations by year
- 2026: 29 · 2025: 61 · 2024: 21 · 2023: 2
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- SSRN Electronic Journal (acceptedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Opinion Dynamics and Social Influence
- Social Sciences › Decision Sciences › Management Science and Operations Research › Simulation Techniques and Applications
- Keywords
- social network simulation, large language models, LLM agents, agent-based modeling, attitude propagation, information dissemination, prompt engineering, fine-tuning, social dynamics, emergence
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.