Saved in:
Bibliographic Details
Main Authors: Lin, Jiacheng, Qian, Kun, Srinivasan, Arvind, Wang, Tian, Han, Fang, Hu, Changran, Liu, Junze, Wang, Ziyi, Xu, Hanwen, Xue, Mengmeng, Yang, Shuo, Zeng, Hansi, Zhan, Simon Sinong, Zhong, Kai, Zhang, Weiqi, Wang, Dakuo, Wang, Tianhao, Li, Zhiyuan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.09794
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915999964463104
author Lin, Jiacheng
Qian, Kun
Srinivasan, Arvind
Wang, Tian
Han, Fang
Hu, Changran
Liu, Junze
Wang, Ziyi
Xu, Hanwen
Xue, Mengmeng
Yang, Shuo
Zeng, Hansi
Zhan, Simon Sinong
Zhong, Kai
Zhang, Weiqi
Wang, Dakuo
Wang, Tianhao
Li, Zhiyuan
author_facet Lin, Jiacheng
Qian, Kun
Srinivasan, Arvind
Wang, Tian
Han, Fang
Hu, Changran
Liu, Junze
Wang, Ziyi
Xu, Hanwen
Xue, Mengmeng
Yang, Shuo
Zeng, Hansi
Zhan, Simon Sinong
Zhong, Kai
Zhang, Weiqi
Wang, Dakuo
Wang, Tianhao
Li, Zhiyuan
contents Personalization today is fundamentally platform-centric: services build user representations from the behavioral fragments they observe. Yet no platform can construct a complete picture of the user, as competitive incentives, legal constraints, user privacy concerns, and epistemic limits create persistent data barriers. This paper argues for a shift from platform-centric personalization to user-governed personalization, where only the user can integrate fragmented contexts across platforms and the offline world. The key asymmetry lies in data access: only users can aggregate their own cross-platform and offline information. Large language model (LLM) agents make such integration practically feasible for the first time by enabling reasoning over heterogeneous personal data and transforming users' cross-context information into actionable personalization capabilities. We provide proof-of-concept evidence that users equipped with cross-platform data exports and an off-the-shelf LLM agent can outperform single-platform personalization baselines. We conclude by outlining a research agenda for building scalable user-governed personalization systems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_09794
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries
Lin, Jiacheng
Qian, Kun
Srinivasan, Arvind
Wang, Tian
Han, Fang
Hu, Changran
Liu, Junze
Wang, Ziyi
Xu, Hanwen
Xue, Mengmeng
Yang, Shuo
Zeng, Hansi
Zhan, Simon Sinong
Zhong, Kai
Zhang, Weiqi
Wang, Dakuo
Wang, Tianhao
Li, Zhiyuan
Information Retrieval
Personalization today is fundamentally platform-centric: services build user representations from the behavioral fragments they observe. Yet no platform can construct a complete picture of the user, as competitive incentives, legal constraints, user privacy concerns, and epistemic limits create persistent data barriers. This paper argues for a shift from platform-centric personalization to user-governed personalization, where only the user can integrate fragmented contexts across platforms and the offline world. The key asymmetry lies in data access: only users can aggregate their own cross-platform and offline information. Large language model (LLM) agents make such integration practically feasible for the first time by enabling reasoning over heterogeneous personal data and transforming users' cross-context information into actionable personalization capabilities. We provide proof-of-concept evidence that users equipped with cross-platform data exports and an off-the-shelf LLM agent can outperform single-platform personalization baselines. We conclude by outlining a research agenda for building scalable user-governed personalization systems.
title LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries
topic Information Retrieval
url https://arxiv.org/abs/2605.09794