用事件驱动记忆模拟用户行为随时间演变，更真实地还原个性变化。
TWICE: Modeling the Temporal Evolution of Personalized User Behavior via Event-Driven Agents
- 基于事件构建记忆模块，追踪人生大事对行为的影响
- 在推特数据集上表现优于现有基线模型，提升真实性与一致性
- 适合研究个性化交互、长期行为建模的学者与工程师
用户模拟器广泛用于数据生成、评估和基于代理的交互，但现有方法常将用户视为静态人格或依赖通用历史上下文，难以捕捉个体行为随时间的演变。为此，我们提出 TWICE——一种基于大语言模型的时序化个性化用户模拟框架。该框架结合结构化用户画像、围绕人生事件和行为转变组织的事件驱动记忆模块，以及分两阶段的流程：先进行事件锚定的内容规划，再进行个性化风格适配。这一设计使模拟器不仅能预测用户说什么，还能体现过往经历如何塑造后续表达。我们在大规模纵向推特数据集上评估 TWICE，并引入综合评估框架，联合衡量真实性、一致性与类人程度。结果表明，TWICE持续优于多个强基线模型，说明以事件为中心的记忆机制是建模个性化行为时序演化的有效路径。
原文摘要 · Abstract (English)
User simulators are widely used for data generation, evaluation, and agent-based interaction, but existing approaches often model users as static personas or rely on generic historical context, making it difficult to capture how individual behavior evolves over time. To address this limitation, we propose TWICE, an LLM-based framework for temporally grounded personalized user simulation. TWICE combines structured user profiling, an event-driven memory module organized around life events and behavioral shifts, and a two-stage workflow separating event-grounded content planning from personalized style adaptation. This design enables the simulator to model not only what a user says, but also how past experiences shape later expression. We evaluate TWICE on a large-scale longitudinal Twitter dataset and introduce a comprehensive evaluation framework that jointly measures authenticity, consistency, and humanlikeness. Results show that TWICE consistently outperforms strong baselines, suggesting that event-centered memory is a promising mechanism for modeling the temporal evolution of personalized user behavior.
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。