arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.05656cs.AI
收藏

HAG:基于主题自适应的分层人口树状代理生成

HAG: Hierarchical Demographic Tree-based Agent Generation for Topic-Adaptive Simulation

State Key Laboratory of AI Safety, Institute of Computing Technology, CAS(中国科学院计算技术研究所人工智能安全国家重点实验室);University of Chinese Academy of Sciences(中国科学院大学);School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学前沿交叉科学学院)

Rongxin Chen, Tianyu Wu, Bingbing Xu, Jiatang Luo, Xiucheng Xu, Huawei Shen

AI总结:

本文提出HAG框架,通过分层决策过程生成符合主题需求的代理群体,提升宏观分布与微观一致性。实验表明HAG在减少群体对齐误差和增强社会一致性方面表现优异。

摘要:

高保真代理初始化对跨领域基于代理的建模至关重要。一个稳健的框架应具备主题自适应性,捕捉宏观层面的联合分布,同时确保微观层面个体的理性。现有方法分为两类:基于静态数据的检索方法无法适应未见主题,而基于大语言模型的方法缺乏宏观分布意识,导致微观层面人物属性与现实不一致。为解决这些问题,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条件概率以构建主题自适应树,实现宏观分布对齐。然后,基于现实世界数据进行实例化和代理增强,确保微观一致性。鉴于缺乏专门评估,我们建立了多领域基准和综合PACE评估框架。大量实验表明,HAG显著优于代表性基线,平均减少群体对齐误差37.7%,增强社会一致性18.8%。

英文摘要:

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%.

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。

↑