PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Minjia, Wang, Yunfeng, Ma, Xiao, Lv, Dexin, Guo, Qifan, Zheng, Lynn, Wang, Benliang, Wang, Lei, Li, Jiannan, Xing, Yongwei, Xu, David, Sun, Zheng
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908881999888384
author Wang, Minjia
Wang, Yunfeng
Ma, Xiao
Lv, Dexin
Guo, Qifan
Zheng, Lynn
Wang, Benliang
Wang, Lei
Li, Jiannan
Xing, Yongwei
Xu, David
Sun, Zheng
author_facet Wang, Minjia
Wang, Yunfeng
Ma, Xiao
Lv, Dexin
Guo, Qifan
Zheng, Lynn
Wang, Benliang
Wang, Lei
Li, Jiannan
Xing, Yongwei
Xu, David
Sun, Zheng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11955
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents
Wang, Minjia
Wang, Yunfeng
Ma, Xiao
Lv, Dexin
Guo, Qifan
Zheng, Lynn
Wang, Benliang
Wang, Lei
Li, Jiannan
Xing, Yongwei
Xu, David
Sun, Zheng
Computation and Language
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.
title PersonaTrace: Synthesizing Realistic Digital Footprints with LLM Agents
topic Computation and Language
url https://arxiv.org/abs/2603.11955