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!
Table of 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.