构建分层人口树生成虚拟人群，让模拟更真实可信。
HAG: Hierarchical Demographic Tree-based Agent Generation for Topic-Adaptive Simulation
- 分两阶段生成：先建主题自适应树，再用真实数据精调个体。
- 相比基线，群体分布误差降37.7%，社会一致性提升18.8%。
- 适合需要高保真人类行为模拟的社科、城市规划等领域。
高保真代理初始化对跨领域的可信代理模型至关重要。理想框架应具备主题自适应能力，既要捕捉宏观层面的联合分布，又要保证微观层面个体行为的合理性。现有方法分为两类：基于静态数据检索的方法无法适应未见主题；基于大语言模型的生成方法缺乏宏观分布感知，导致个体属性与现实不符。为此，我们提出HAG——一种分层代理生成框架，将人口生成形式化为两阶段决策过程。首先利用世界知识模型推断层次化条件概率，构建主题自适应树，实现宏观分布对齐；随后基于真实世界数据进行实例化与智能体增强，确保微观一致性。针对评估缺失问题，我们建立多领域基准和全面的PACE评估框架。大量实验表明，HAG显著优于代表性基线，在平均降低37.7%的人口分布误差的同时，提升18.8%的社会学一致性。
原文摘要 · Abstract (English)
High-fidelity agent initialization is crucial for credible Agent-Based Modeling across diverse domains. A robust framework should be Topic-Adaptive, capturing macro-level joint distributions while ensuring micro-level individual rationality. Existing approaches fall into two categories: static data-based retrieval methods that fail to adapt to unseen topics absent from the data, and LLM-based generation methods that lack macro-level distribution awareness, resulting in inconsistencies between micro-level persona attributes and reality. To address these problems, we propose HAG, a Hierarchical Agent Generation framework that formalizes population generation as a two-stage decision process. Firstly, utilizing a World Knowledge Model to infer hierarchical conditional probabilities to construct the Topic-Adaptive Tree, achieving macro-level distribution alignment. Then, grounded real-world data, instantiation and agentic augmentation are carried out to ensure micro-level consistency. Given the lack of specialized evaluation, we establish a multi-domain benchmark and a comprehensive PACE evaluation framework. Extensive experiments show that HAG significantly outperforms representative baselines, reducing population alignment errors by an average of 37.7% and enhancing sociological consistency by 18.8%.
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。