mlsanityData to 14 Oct 2026

AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side

arXiv 2609.31166 ↗First posted 25 Sep 2026cs.IR cs.AI cs.DBcited by 0

On the map: LLM agents and tool use → Agentic recommender systems

Abstract (arXiv)

Recommender systems have traditionally been developed for platforms. However, this has given rise to many phenomena that may be advantageous for platform lock-in but are a nuisance to users, such as clickbait, filter bubbles, and the spread of fake news. Recently, user-side recommender systems have been proposed as a new paradigm for solving this problem. If users deploy their own recommender systems, they are no longer at the mercy of the platform's interests. However, building a user-side recommender system is not trivial; in particular, customizing one for oneself requires additional data. We propose AgentRecommender, a method that leverages the investigation capability and internal knowledge of LLM agents to flexibly build user-side recommender systems without additional data. AgentRecommender allows users to easily create recommender systems tailored to their own preferences.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use. Builds on 42 of its 68 references that are in the map. First posted on arXiv 25 Sep 2026.

Builds on

42 of 68 references.

Closest ancestors · 10

Same direction, newest first

  1. 2026Personalized Recommendation Tool Learning via Autonomous Language Agents22 Jul
  2. 2026Position: Recommender Systems Should Move Beyond Platform-Centric Ranking toward Personal Agent-Mediated Recommendation21 Jul
  3. 2026HARPO: Hierarchical Agentic Reasoning for User-Aligned Conversational Recommendation11 Apr
  4. 2026RecThinker: An Agentic Framework for Tool-Augmented Reasoning in Recommendation10 Mar
  5. 2025AgentDR: Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents7 Oct
  6. 2025Thought-Augmented Planning for LLM-Powered Interactive Recommender Agent30 Jun
  7. 2025ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation27 Jun
  8. 2025iAgent: LLM Agent as a Shield between User and Recommender Systems20 Feb
  9. 2025AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations19 Feb
  10. 2023AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems13 Oct

Other references · 32

  1. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  2. 2015Image-based Recommendations on Styles and Substitutescited by 706
  3. 2016Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filteringcited by 520
  4. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 369
  5. 2018Fairness of Exposure in Rankingscited by 190
  6. 2023User Behavior Simulation with Large Language Model based Agentscited by 140
  7. 2019Fairness in Recommendation Ranking through Pairwise Comparisonscited by 127
  8. 2018Equity of Attention: Amortizing Individual Fairness in Rankingscited by 124
  9. 2017FA*IR: A Fair Top-k Ranking Algorithmcited by 113
  10. 2017Beyond Parity: Fairness Objectives for Collaborative Filteringcited by 93
  11. 2020Fairness-Aware Explainable Recommendation over Knowledge Graphscited by 74
  12. 2017Multisided Fairness for Recommendationcited by 70
20 more
  1. 2018Exploring Author Gender in Book Rating and Recommendationcited by 29
  2. 2023Embarrassingly Simple Text Watermarkscited by 29
  3. 2022An Audit of Misinformation Filter Bubbles on YouTube: Bubble Bursting and Recent Behavior Changescited by 15
  4. 2019Beyond Personalization: Social Content Recommendation for Creator Equality and Consumer Satisfactioncited by 14
  5. 2020Algorithmic Decision Making with Conditional Fairnesscited by 14
  6. 2025MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMscited by 9
  7. 2025Think before Recommendation: Autonomous Reasoning-enhanced Recommendercited by 9
  8. 2021Private Recommender Systems: How Can Users Build Their Own Fair Recommender Systems without Log Data?cited by 7
  9. 2022Towards Principled User-side Recommender Systemscited by 7
  10. 2021Retrieving Black-box Optimal Images from External Databasescited by 6
  11. 2022CLEAR: A Fully User-side Image Search Systemcited by 6
  12. 2025Bonsai: Intentional and Personalized Social Media Feedscited by 6
  13. 2025Preserving Privacy and Utility in LLM-Based Product Recommendationscited by 5
  14. 2025Alexandria: A Library of Pluralistic Values for Realtime Re-Ranking of Social Media Feedscited by 5
  15. 2025Value Alignment of Social Media Ranking Algorithmscited by 4
  16. 2023Making Translators Privacy-aware on the User's Sidecited by 3
  17. 2024User-Side Realizationcited by 3
  18. 2024Overhead-free User-side Recommender Systemscited by 2
  19. 2026The Prosocial Ranking Challenge: Reducing Polarization on Social Media without Sacrificing Engagementcited by 2
  20. 2025Solving the Cold Start Problem on One's Own as an End User via Preference Transfercited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
  2. 2025A Survey on LLM-powered Agents for Recommender Systems
  3. 2026Do Recommendation Algorithms Work When Users Are LLM Agents? A Case Study on Moltbook
  4. 2025RecoWorld: Building Simulated Environments for Agentic Recommender Systems
  5. 2025Multi-Agent Collaborative Filtering: Orchestrating Users and Items for Agentic Recommendations
  6. 2024Prospect Personalized Recommendation on Large Language Model-based Agent Platform
  7. 2023On Generative Agents in Recommendation
  8. 2026From Hidden Profiles to Governable Personalization: Recommender Systems in the Age of LLM Agents