LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries

TL;DR

This paper advocates for user-governed personalization leveraging LLM agents to integrate cross-platform and offline data, overcoming platform-centric limitations and enhancing personalization capabilities.

Contribution

It introduces a novel approach where LLM agents enable users to unify fragmented personal data for personalized experiences beyond individual platforms.

Findings

Users with cross-platform data and LLM agents outperform single-platform baselines.

LLM agents facilitate reasoning over heterogeneous personal data.

Proof-of-concept demonstrates practical feasibility of user-governed personalization.

Abstract

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.