Interactive, multi-agent social simulation systems have shown promise for helping users practice navigating various complex social situations across domains. This paper asks: To what extent can such systems help young adult (YA) bystanders speak up publicly against cyberbullying, a task often thwarted by complex, multi-party social dynamics? We created Upstanders' Practicum, a multi-AI-agent social media simulation powered by Large Language Models (LLMs), as a probe and observed 34 YAs freely practicing public bystander intervention across three iteratively refined versions. We found that practicing public bystander intervention in the simulation was helpful, but after participants made three attention shifts: (1) from inattention to paying true attention, (2) from self-focus ("I don't usually do this'') to attending to those directly involved, and (3) from resolving the private conflict between bully and victim ("maybe I could set up the meeting between them'') to addressing the broader audience online ("public comment is about norm-setting"). Only after these shifts did practice in the simulation start to help: participants then saw a reason to speak up publicly and, through continued practice, crafted tactful public messages without explicit instruction. These findings illuminate new design and research opportunities for bystander education beyond social skill instruction, namely, designing for true attention, for fostering a vocal upstander identity, and for seeing bystander intervention as public norm setting. In addition, we open-source Truman Agents (cornell-design-aigroup.github.io/TrumanAgents/), the first-of-its-kind multi-LLM-agent social media simulation platform that Upstanders' Practicum builds upon, for future cyberbullying and social media research.

翻译：交互式、多智能体社会模拟系统在帮助用户练习应对跨领域的各种复杂社交情境方面展现出潜力。本文探讨：这类系统在多大程度上能帮助年轻成年人旁观者公开反对网络欺凌？——这一行为常因多方交织的社交动态而受阻。我们构建了"Upstanders' Practicum"（支持者实训场），这是一个基于大语言模型驱动的多AI智能体社交媒体模拟平台，作为研究探针，观察34名年轻成年人在三个迭代优化版本中自由练习公开旁观者干预的过程。研究发现，在模拟中练习公开旁观者干预具有助益，但需经历三次注意力转变：（1）从"无关注"转向"真实关注"；（2）从"自我聚焦"（"我通常不这样做"）转向关注直接涉事方；（3）从"化解欺凌者与受害者间的私下冲突"（"或许我可以安排他们见面"）转向处理线上更广泛的受众（"公开评论关乎规范塑造"）。只有经历这些转变后，模拟练习才真正发挥作用：参与者开始意识到公开表态的必要性，并通过持续练习，在无明确指导的情况下形成得体的公开回应。这些发现揭示了超越社交技能教学的旁观者教育新设计与研究机遇，即：设计激发真实关注、培养敢于发声的支持者身份认同、将旁观者干预视为公共规范塑造的过程。此外，我们开源了Truman Agents（cornell-design-aigroup.github.io/TrumanAgents/）——这是首个支持多项大语言模型智能体的社交媒体模拟平台，也是"Upstanders' Practicum"的构建基础，旨在为未来网络欺凌与社交媒体研究提供支持。