用知识与文化约束模拟复杂新闻事件，提升预测与应对能力。
Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play
- 基于事件模板与用户假设，构建可控制的多智能体仿真系统。
- 引入地理多样性的常识与文化规范，增强模拟情境的合理性。
- 适合应急响应、公共政策制定者参考，提升决策准备度。
复杂新闻事件（如自然灾害、社会政治冲突）需要政府与社会快速响应。依赖历史事件进行未来推演不足，因事件稀少且无法覆盖所有情景。我们开发了一种受事件模式（event schema）和用户提供的具体假设引导的可控复杂事件模拟器。由于事件动态受细粒度社会文化背景影响，我们进一步引入了地理多样性常识与文化规范感知的知识增强模块。为提升模拟连贯性，除全局事件时间线外，采用多智能体方法模拟个体角色的状态、计划与行动。结合事件模式与文化规范，生成的模拟结果在连贯性与适当性上显著提升，并获得人道主义援助组织参与者的一致好评。
原文摘要 · Abstract (English)
Complex news events, such as natural disasters and socio-political conflicts, require swift responses from the government and society. Relying on historical events to project the future is insufficient as such events are sparse and do not cover all possible conditions and nuanced situations. Simulation of these complex events can help better prepare and reduce the negative impact. We develop a controllable complex news event simulator guided by both the event schema representing domain knowledge about the scenario and user-provided assumptions representing case-specific conditions. As event dynamics depend on the fine-grained social and cultural context, we further introduce a geo-diverse commonsense and cultural norm-aware knowledge enhancement component. To enhance the coherence of the simulation, apart from the global timeline of events, we take an agent-based approach to simulate the individual character states, plans, and actions. By incorporating the schema and cultural norms, our generated simulations achieve much higher coherence and appropriateness and are received favorably by participants from a humanitarian assistance organization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。