LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries
For users and researchers, this work introduces a new paradigm for personalization that overcomes data barriers across platforms, though it is currently at the proof-of-concept stage.
The paper proposes shifting from platform-centric to user-governed personalization, where users integrate their own cross-platform and offline data using LLM agents. Proof-of-concept results show that users with cross-platform data exports and an off-the-shelf LLM agent can outperform single-platform personalization baselines.
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.