arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.00994cs.AIcs.CY
收藏

ElecTwit:多智能体社交系统中说服研究的框架

ElecTwit: A Framework for Studying Persuasion in Multi-Agent Social Systems

Georgia Institute of Technology(佐治亚理工学院)

Michael Bao

AI总结:

ElecTwit通过模拟政治选举中的社交媒体互动,研究多智能体系统中说服现象的影响因素及不同模型架构对说服动态的作用。

摘要:

本文介绍了ElecTwit,一个用于研究多智能体系统中说服现象的模拟框架,旨在模拟社交媒体平台上政治选举期间的互动。通过在现实环境中进行实验,我们旨在克服以往研究中常使用的基于游戏的模拟方法的局限性。我们观察到大多数测试的LLMs广泛使用了25种特定的说服技巧,范围比之前报告的更广。模型间在技巧使用和整体说服输出上的差异突显了不同的模型架构和训练如何影响现实社交模拟中的动态。此外,我们还观察到一些独特现象,如“真理核心”信息和具有“墨水”痴迷的自发发展,其中智能体集体要求书面证明。本研究为在现实世界中评估说服LLM代理提供了基础,确保一致性并防止危险后果。

英文摘要:

This paper introduces ElecTwit, a simulation framework designed to study persuasion within multi-agent systems, specifically emulating the interactions on social media platforms during a political election. By grounding our experiments in a realistic environment, we aimed to overcome the limitations of game-based simulations often used in prior research. We observed the comprehensive use of 25 specific persuasion techniques across most tested LLMs, encompassing a wider range than previously reported. The variations in technique usage and overall persuasion output between models highlight how different model architectures and training can impact the dynamics in realistic social simulations. Additionally, we observed unique phenomena such as "kernel of truth" messages and spontaneous developments with an "ink" obsession, where agents collectively demanded written proof. Our study provides a foundation for evaluating persuasive LLM agents in real-world contexts, ensuring alignment and preventing dangerous outcomes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑