Research

Paper

AI LLM March 12, 2026

PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents

Authors

Minjia Wang, Yunfeng Wang, Xiao Ma, Dexin Lv, Qifan Guo, Lynn Zheng, Benliang Wang, Lei Wang, Jiannan Li, Yongwei Xing, David Xu, Zheng Sun

Abstract

Digital footprints (records of individuals' interactions with digital systems) are essential for studying behavior, developing personalized applications, and training machine learning models. However, research in this area is often hindered by the scarcity of diverse and accessible data. To address this limitation, we propose a novel method for synthesizing realistic digital footprints using large language model (LLM) agents. Starting from a structured user profile, our approach generates diverse and plausible sequences of user events, ultimately producing corresponding digital artifacts such as emails, messages, calendar entries, reminders, etc. Intrinsic evaluation results demonstrate that the generated dataset is more diverse and realistic than existing baselines. Moreover, models fine-tuned on our synthetic data outperform those trained on other synthetic datasets when evaluated on real-world out-of-distribution tasks.

Metadata

arXiv ID: 2603.11955
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-03-12
Fetched: 2026-03-14 05:03

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.11955v1</id>\n    <title>PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents</title>\n    <updated>2026-03-12T14:02:24Z</updated>\n    <link href='https://arxiv.org/abs/2603.11955v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.11955v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Digital footprints (records of individuals' interactions with digital systems) are essential for studying behavior, developing personalized applications, and training machine learning models. However, research in this area is often hindered by the scarcity of diverse and accessible data. To address this limitation, we propose a novel method for synthesizing realistic digital footprints using large language model (LLM) agents. Starting from a structured user profile, our approach generates diverse and plausible sequences of user events, ultimately producing corresponding digital artifacts such as emails, messages, calendar entries, reminders, etc. Intrinsic evaluation results demonstrate that the generated dataset is more diverse and realistic than existing baselines. Moreover, models fine-tuned on our synthetic data outperform those trained on other synthetic datasets when evaluated on real-world out-of-distribution tasks.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-12T14:02:24Z</published>\n    <arxiv:comment>EACL 2026 Industry Track</arxiv:comment>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Minjia Wang</name>\n    </author>\n    <author>\n      <name>Yunfeng Wang</name>\n    </author>\n    <author>\n      <name>Xiao Ma</name>\n    </author>\n    <author>\n      <name>Dexin Lv</name>\n    </author>\n    <author>\n      <name>Qifan Guo</name>\n    </author>\n    <author>\n      <name>Lynn Zheng</name>\n    </author>\n    <author>\n      <name>Benliang Wang</name>\n    </author>\n    <author>\n      <name>Lei Wang</name>\n    </author>\n    <author>\n      <name>Jiannan Li</name>\n    </author>\n    <author>\n      <name>Yongwei Xing</name>\n    </author>\n    <author>\n      <name>David Xu</name>\n    </author>\n    <author>\n      <name>Zheng Sun</name>\n    </author>\n  </entry>"
}