mlsanityData to 14 Oct 2026

Breaking the Filter Bubble: A Semantic Pareto-DQN Framework for Multi-Objective Recommendation

arXiv 2606.24042 ↗First posted 23 Jun 2026cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Recommender systems often induce filter bubbles and semantic homogenization by monolithically optimizing for immediate user engagement. Standard single-objective models, including traditional Deep Q-Networks, are ill-equipped to navigate the trade-offs between platform retention and critical societal values like information diversity and provider fairness. To address these limitations, we introduce a multi-objective reinforcement learning framework that formalizes recommendation as a semantic multi-objective Markov decision process. By integrating high-fidelity semantic embeddings with a Pareto-DQN agent, our architecture treats engagement, diversity, and fairness as distinct, non-aggregable reward signals, avoiding the pitfalls of static reward scalarization. Empirical evaluations on the MovieLens small dataset shows that our hypervolume based action selection disrupts the feedback loops responsible for semantic collapse. By sustaining high state-trajectory variance, the Pareto-DQN effectively maps the Pareto frontier, achieving gains in auxiliary societal objectives with only marginal impacts on engagement. This work provides a path toward intrinsically aligned, responsible recommender systems.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 11 of its 21 references that are in the map. First posted on arXiv 23 Jun 2026.

Builds on

11 of 21 references.

References · 11

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2021A Practical Guide to Multi-Objective Reinforcement Learning and Planningcited by 256
  3. 2020pymoo: Multi-objective Optimization in Pythoncited by 200
  4. 2021Reinforcement learning based recommender systems: A surveycited by 188
  5. 2018Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modelingcited by 31
  6. 2022Toward Pareto Efficient Fairness-Utility Trade-off inRecommendation through Reinforcement Learningcited by 29
  7. 2021Intelligent Electric Vehicle Charging Recommendation Based on Multi-Agent Reinforcement Learningcited by 20
  8. 2023Two-Stage Constrained Actor-Critic for Short Video Recommendationcited by 16
  9. 2021Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learningcited by 14
  10. 2024Sequential Recommendation for Optimizing Both Immediate Feedback and Long-term Retentioncited by 10
  11. 2024Deep Pareto Reinforcement Learning for Multi-Objective Recommender Systemscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Anomaly Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-Enhanced Reinforcement Learning for Long-Term User Satisfaction in Interactive Recommendation
  2. 2021Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation
  3. 2025Breaking the Cold-Start Barrier: Reinforcement Learning with Double and Dueling DQNs
  4. 2025Reward Balancing Revisited: Enhancing Offline Reinforcement Learning for Recommender Systems
  5. 2023Robust Reinforcement Learning Objectives for Sequential Recommender Systems
  6. 2025Fine-Tuning Diffusion-Based Recommender Systems via Reinforcement Learning with Reward Function Optimization
  7. 2026Fairness Begins with State: Purifying Latent Preferences for Hierarchical Reinforcement Learning in Interactive Recommendation
  8. 2025Refine-POI: Reinforcement Fine-Tuned Large Language Models for Next Point-of-Interest Recommendation