# From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents

arXiv: https://arxiv.org/abs/2604.20065 · HTML: https://mlsanity.com/paper/2604.20065/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 19 of 19)

- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Explainable Recommendation: A Survey and New Perspectives](https://mlsanity.com/paper/1804.11192/) (2018)
- [A Survey on Conversational Recommender Systems](https://mlsanity.com/paper/2004.00646/) (2020)
- [A Comprehensive Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2209.10117/) (2022)
- [Personalized Graph Signal Processing for Collaborative Filtering](https://mlsanity.com/paper/2302.02113/) (2023)
- [AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations](https://mlsanity.com/paper/2502.13843/) (2025)
- [Digital Nudging with Recommender Systems: Survey and Future Directions](https://mlsanity.com/paper/2011.03413/) (2020)
- [A Survey on Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2401.04971/) (2024)
- [AutoSeqRec: Autoencoder for Efficient Sequential Recommendation](https://mlsanity.com/paper/2308.06878/) (2023)
- [Triple Structural Information Modelling for Accurate, Explainable and Interactive Recommendation](https://mlsanity.com/paper/2304.11528/) (2023)
- [Improving LLM-powered Recommendations with Personalized Information](https://mlsanity.com/paper/2502.13845/) (2025)
- [Unbiased Collaborative Filtering with Fair Sampling](https://mlsanity.com/paper/2502.13840/) (2025)
- [Bidirectional Knowledge Distillation for Enhancing Sequential Recommendation with Large Language Models](https://mlsanity.com/paper/2505.18120/) (2025)
- [Dynamic Feature-Embedding Communication via Codebook Distillation for Federated Recommendation](https://mlsanity.com/paper/2601.18570/) (2026)
- [Drift-Aware Continual Tokenization for Generative Recommendation](https://mlsanity.com/paper/2603.29705/) (2026)

## Built on by (most cited first, 3 of 3)

- [The User Asks, Platforms Compete: How Agentic Recommendation Markets Take Shape](https://mlsanity.com/paper/2607.25253/) (2026)
- [ElderBench: Benchmarking Autonomous Mobile Agents for Older Adults](https://mlsanity.com/paper/2609.04850/) (2026)
- [Personal-Agent Mediated Recommendation with Cross-Platform User History](https://mlsanity.com/paper/2610.07588/) (2026)

## Abstract (arXiv)

Personalization has traditionally depended on platform-specific user models that are optimized for prediction but remain largely inaccessible to the people they describe. As LLM-based assistants increasingly mediate search, shopping, travel, and content access, this arrangement may be giving way to a new personalization stack in which user representation is no longer confined to isolated platforms. In this paper, we argue that the key issue is not simply that large language models can enhance recommendation quality, but that they reconfigure where and how user representations are produced, exposed, and acted upon. We propose a shift from hidden platform profiling toward governable personalization, where user representations may become more inspectable, revisable, portable, and consequential across services. Building on this view, we identify five research fronts for recommender systems: transparent yet privacy-preserving user modeling, intent translation and alignment, cross-domain representation and memory design, trustworthy commercialization in assistant-mediated environments, and operational mechanisms for ownership, access, and accountability. We position these not as isolated technical challenges, but as interconnected design problems created by the emergence of LLM agents as intermediaries between users and digital platforms. We argue that the future of recommender systems will depend not only on better inference, but on building personalization systems that users can meaningfully understand, shape, and govern.