ArXiv TLDR

LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries

🐦 Tweet
2605.09794

Jiacheng Lin, Kun Qian, Arvind Srinivasan, Tian Wang, Fang Han + 13 more

cs.IR

TLDR

LLM agents empower users to integrate and govern their personal data across platforms, moving beyond fragmented, platform-centric personalization.

Key contributions

  • Proposes user-governed personalization, shifting from fragmented platform-centric models.
  • LLM agents integrate diverse personal data across platforms and offline contexts.
  • Proof-of-concept shows LLM agents outperform single-platform personalization baselines.

Why it matters

This paper introduces a paradigm shift in personalization, empowering users to control their data across platforms. By leveraging LLM agents, it offers a path towards more comprehensive and privacy-respecting personalization, overcoming current data silos.

Original 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.

📬 Weekly AI Paper Digest

Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.