arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.22222cs.IRcs.MA
收藏

TWICE:通过事件驱动代理建模个性化用户行为的时间演化

TWICE: Modeling the Temporal Evolution of Personalized User Behavior via Event-Driven Agents

SJTU Paris Elite Institute of Technology (SPEIT), Shanghai Jiao Tong University(上海交通大学巴黎卓越工程师学院);X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机学院;人工智能研究院(教育部人工智能重点实验室));MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University

Bingrui Jin, Kunyao Lan, Baihan LI, Mengyue Wu

AI总结:

提出TWICE框架,结合结构化用户画像、事件驱动记忆模块和两阶段工作流,利用LLM模拟用户行为的时间演化,在Twitter数据集上优于基线。

摘要:

用户模拟器广泛用于数据生成、评估和基于代理的交互,但现有方法通常将用户建模为静态角色或依赖通用历史上下文,难以捕捉个体行为随时间的变化。为解决这一局限,我们提出TWICE,一个基于LLM的框架,用于时间基础的个人化用户模拟。TWICE结合了结构化用户画像、围绕生活事件和行为转变组织的事件驱动记忆模块,以及将事件基础内容规划与个性化风格适应分离的两阶段工作流。这种设计使模拟器不仅能建模用户说什么,还能建模过去经历如何影响后续表达。我们在大规模纵向Twitter数据集上评估TWICE,并引入了一个综合评估框架,同时衡量真实性、一致性和类人性。结果表明,TWICE始终优于强基线,表明以事件为中心的记忆是建模个性化用户行为时间演化的有前景机制。

英文摘要:

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.

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。

↑