发表机构
Shanghai Innovation Institute; Fudan University; King’s College London; Tongji University; Northwestern Polytechnical University; The London School of Economics and Political Science; The Chinese University of Hong Kong; Singapore Management University; University of Oxford; University of Rochester（上海创新研究院; 复旦大学; 伦敦国王学院; 同济大学; 西北工业大学; 伦敦政治经济学院; 香港中文大学; 新加坡管理大学; 牛津大学; 罗切斯特大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SocioVerse2提出人机协同进化范式，通过纵向模拟与可控研究双循环及智能体基础设施，支持干预与过程控制，并经多案例验证，实现实质性社会科学研究。
AI 中文摘要
社会模拟为社会科学家提供了一种现实世界无法提供的实验工具，而生成式智能体通过充当硅基样本，将基于智能体的建模与真实行为数据相结合，从而变革了这一领域。现有平台验证集体行为，在横截面上使模拟群体与真实社会对齐，并采用自主智能体进行研究流程。然而，两个社会科学需求仍未得到系统性支持：对模拟内容的干预，以及研究者对产生模拟结果过程的控制。我们提出SocioVerse2，它将SocioVerse 1.0扩展为人机协同进化范式，由两个循环和一个基础设施构成。纵向模拟循环通过不断演化的环境模拟目标群体，并通过干预分叉出反事实分支。可控研究循环将研究本身视为可编辑状态，并通过可控编辑更新状态版本。社会科学智能体基础设施通过可组合技能（含研究者检查点）、覆盖五个人格池的群体服务，以及覆盖21个真实世界信号源（具备时点保证）的环境服务，承载这两个循环。我们通过三个案例族和七个案例研究验证了SocioVerse2，从复现经典基于智能体的模型，到基于真实记录建模政策过程，再到在响应模型知识截止日期之后对宏观经济指数进行即时预测。借助人机协同进化范式，这些案例超越了系统演示，成为探究各自学科前沿问题的实质性研究。代码、数据服务和实验工作台已作为开源资源发布。
英文摘要
Social simulation offers the social sciences an experimental instrument that the real world cannot supply, and generative agents have transformed it by acting as silicon samples that unite agent-based modeling with real behavioral data. Existing platforms verify collective behavior, align simulated populations with real societies in cross-sections, and employ autonomous agents for the research process. However, two social science requirements remain without systematic support: intervention in the content of a simulation and the researcher's control over the process that produces it. We present SocioVerse2, which extends SocioVerse 1.0 into a human-AI co-evolutionary paradigm built from two loops and one infrastructure. The longitudinal simulation loop simulates the target population with evolving environments and forks counterfactual branches via interventions. The controllable research loop takes the study itself as an editable state and updates state versions via controllable editing. The social science agentic infrastructure carries both loops through composable skills with researcher checkpoints, a population service over five persona pools, and an environment service over 21 real-world signal sources with point-in-time guarantees. We validate SocioVerse2 across three case families and seven case studies, from reproducing canonical agent-based models to modeling policy processes on real records and nowcasting macro-economic indices beyond the response model's knowledge cutoff. With the human-AI co-evolutionary paradigm, these cases go beyond system demonstrations to become substantive studies that investigate frontier questions in their respective disciplines. Code, data services, and a workbench are released as open-source resources.
CommentsProject page: https://socioverse.fudan-disc.com/
