Multi-Agent Social Simulation: Protocolizing LLM-Driven Agent-Based Modeling as a Quantitative Research Method
AI · 24.07.2026 · 7 (8) · 279
DOI: 10.3390/ai7080279 ↗Kurz gefasst
Fachartikel in der Zeitschrift AI, online erschienen am 24.07.2026. Verfasst von Xiaoli Hu und 1 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Social and behavioral research often needs to examine policy shocks, information interventions, platform-mediated attention, and governance feedback, but direct experiments on real populations are constrained by ethical risks, intervention costs, and limited repeatability. This study proposes Multi-Agent Social Simulation (MASS), a protocolized form of large language model-driven agent-based modeling (LLM-driven ABM) designed as a low-risk, repeatable, and auditable pre-experimental simulation method for quantitative research. MASS embeds LLMs in an agent-based modeling (ABM) framework and uses role settings, round-based scheduling, information control, background-rule control, structured outputs, harness checks, reason-action logs, and replication manifests to transform open-ended language generation into recordable, checkable, and statistically analyzable agent-round observations. The method is evaluated through the New Jersey–Pennsylvania minimum wage natural experiment, the 2016 UK Brexit digital campaigning context, and the 2023 Zibo barbecue tourism public-opinion event. Results show that protocolized LLM-driven ABM can generate analyzable and empirically assessable outputs across policy-shock, information-intervention, and governance-feedback scenarios. The strongest evidence concerns rule-shock identification, declining undecided share under targeting, and mechanism-chain consistency among governance response, public sentiment, and behavioral intention. MASS is not a substitute for real-world experiments or causal inference; it is a pre-experimental simulation method for mechanism rehearsal, risk identification, counterfactual comparison, and research design preparation.
Zitieren
APA
Hu, X., & Shen, Y. (2026). Multi-Agent Social Simulation: Protocolizing LLM-Driven Agent-Based Modeling as a Quantitative Research Method. AI, 7(8), 279. https://doi.org/10.3390/ai7080279
Vancouver
Hu X, Shen Y. Multi-Agent Social Simulation: Protocolizing LLM-Driven Agent-Based Modeling as a Quantitative Research Method. AI. 2026;7(8):279. doi:10.3390/ai7080279
BibTeX
@article{Hu2026,
author = {Hu, Xiaoli and Shen, Yang},
title = {Multi-Agent Social Simulation: Protocolizing LLM-Driven Agent-Based Modeling as a Quantitative Research Method},
journal = {AI},
year = {2026},
volume = {7},
number = {8},
pages = {279},
doi = {10.3390/ai7080279}
}
EUVIMED