Exploring Large Language Model Agents for Piloting Social Experiments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Piao, Jinghua, Yan, Yuwei, Li, Nian, Zhang, Jun, Li, Yong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916892856287232
author Piao, Jinghua
Yan, Yuwei
Li, Nian
Zhang, Jun
Li, Yong
author_facet Piao, Jinghua
Yan, Yuwei
Li, Nian
Zhang, Jun
Li, Yong
contents Computational social experiments, which typically employ agent-based modeling to create testbeds for piloting social experiments, not only provide a computational solution to the major challenges faced by traditional experimental methods, but have also gained widespread attention in various research fields. Despite their significance, their broader impact is largely limited by the underdeveloped intelligence of their core component, i.e., agents. To address this limitation, we develop a framework grounded in well-established social science theories and practices, consisting of three key elements: (i) large language model (LLM)-driven experimental agents, serving as "silicon participants", (ii) methods for implementing various interventions or treatments, and (iii) tools for collecting behavioral, survey, and interview data. We evaluate its effectiveness by replicating three representative experiments, with results demonstrating strong alignment, both quantitatively and qualitatively, with real-world evidence. This work provides the first framework for designing LLM-driven agents to pilot social experiments, underscoring the transformative potential of LLMs and their agents in computational social science
format Preprint
id arxiv_https___arxiv_org_abs_2508_08678
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Large Language Model Agents for Piloting Social Experiments
Piao, Jinghua
Yan, Yuwei
Li, Nian
Zhang, Jun
Li, Yong
Computers and Society
Computational social experiments, which typically employ agent-based modeling to create testbeds for piloting social experiments, not only provide a computational solution to the major challenges faced by traditional experimental methods, but have also gained widespread attention in various research fields. Despite their significance, their broader impact is largely limited by the underdeveloped intelligence of their core component, i.e., agents. To address this limitation, we develop a framework grounded in well-established social science theories and practices, consisting of three key elements: (i) large language model (LLM)-driven experimental agents, serving as "silicon participants", (ii) methods for implementing various interventions or treatments, and (iii) tools for collecting behavioral, survey, and interview data. We evaluate its effectiveness by replicating three representative experiments, with results demonstrating strong alignment, both quantitatively and qualitatively, with real-world evidence. This work provides the first framework for designing LLM-driven agents to pilot social experiments, underscoring the transformative potential of LLMs and their agents in computational social science
title Exploring Large Language Model Agents for Piloting Social Experiments
topic Computers and Society
url https://arxiv.org/abs/2508.08678