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.
@article{arxiv.2605.09794,
title = {LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries},
author = {Jiacheng Lin and Kun Qian and Arvind Srinivasan and Tian Wang and Fang Han and Changran Hu and Junze Liu and Ziyi Wang and Hanwen Xu and Mengmeng Xue and Shuo Yang and Hansi Zeng and Simon Sinong Zhan and Kai Zhong and Weiqi Zhang and Dakuo Wang and Tianhao Wang and Zhiyuan Li},
journal= {arXiv preprint arXiv:2605.09794},
year = {2026}
}