{"total":71,"rows":[{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2505.14069","title":"Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning","created":"2025-05-20","cited_by_count":70,"area":"rag"},{"id":"2108.05552","title":"Graph Trend Filtering Networks for Recommendations","created":"2021-08-12","cited_by_count":53,"area":null},{"id":"2503.24289","title":"Rec-R1: Bridging Generative Large Language Models and User-Centric Recommendation Systems via Reinforcement Learning","created":"2025-03-31","cited_by_count":33,"area":null},{"id":"2106.06713","title":"AutoLoss: Automated Loss Function Search in Recommendations","created":"2021-06-12","cited_by_count":31,"area":null},{"id":"2504.10147","title":"A Survey of Personalization: From RAG to Agent","created":"2025-04-14","cited_by_count":27,"area":"rag"},{"id":"2302.03328","title":"Multi-Task Recommendations with Reinforcement Learning","created":"2023-02-07","cited_by_count":26,"area":null},{"id":"2109.04083","title":"User Tampering in Reinforcement Learning Recommender Systems","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2504.14587","title":"Generative Auto-Bidding with Value-Guided Explorations","created":"2025-04-20","cited_by_count":23,"area":null},{"id":"2109.03540","title":"A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions","created":"2021-09-08","cited_by_count":21,"area":null},{"id":"2204.06127","title":"Reinforcement learning on graphs: A survey","created":"2022-04-13","cited_by_count":20,"area":null},{"id":"2310.00678","title":"A General Offline Reinforcement Learning Framework for Interactive Recommendation","created":"2023-10-01","cited_by_count":18,"area":"offlinerl"},{"id":"2312.15450","title":"Agent4Ranking: Semantic Robust Ranking via Personalized Query Rewriting Using Multi-agent LLM","created":"2023-12-24","cited_by_count":18,"area":"agents"},{"id":"2111.05897","title":"Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters","created":"2021-11-10","cited_by_count":17,"area":null},{"id":"2407.12448","title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning","created":"2024-07-17","cited_by_count":17,"area":"diffusion"},{"id":"2109.08331","title":"Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation","created":"2021-09-17","cited_by_count":16,"area":"offlinerl"},{"id":"2302.01680","title":"Two-Stage Constrained Actor-Critic for Short Video Recommendation","created":"2023-02-03","cited_by_count":16,"area":null},{"id":"2302.01724","title":"Reinforcing User Retention in a Billion Scale Short Video Recommender System","created":"2023-02-03","cited_by_count":15,"area":null},{"id":"2504.18383","title":"Bridge the Domains: Large Language Models Enhanced Cross-domain Sequential Recommendation","created":"2025-04-25","cited_by_count":15,"area":null},{"id":"2110.15097","title":"Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning","created":"2021-10-28","cited_by_count":14,"area":null},{"id":"2304.07920","title":"Causal Decision Transformer for Recommender Systems via Offline Reinforcement Learning","created":"2023-04-17","cited_by_count":11,"area":"offlinerl"},{"id":"2510.08935","title":"Personalize Before Retrieve: LLM-based Personalized Query Expansion for User-Centric Retrieval","created":"2025-10-10","cited_by_count":11,"area":"rag"},{"id":"2109.03150","title":"Recommendation Fairness: From Static to Dynamic","created":"2021-09-05","cited_by_count":10,"area":null},{"id":"2206.02620","title":"ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor","created":"2022-06-01","cited_by_count":10,"area":null},{"id":"2108.09141","title":"Reinforcement Learning to Optimize Lifetime Value in Cold-Start Recommendation","created":"2021-08-20","cited_by_count":9,"area":null},{"id":"2212.11431","title":"Local Policy Improvement for Recommender Systems","created":"2022-12-22","cited_by_count":9,"area":null},{"id":"2402.15164","title":"EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender Systems","created":"2024-02-23","cited_by_count":9,"area":"deeprl"},{"id":"2111.03474","title":"Supervised Advantage Actor-Critic for Recommender Systems","created":"2021-11-05","cited_by_count":8,"area":null},{"id":"2202.03867","title":"Offline Reinforcement Learning for Mobile Notifications","created":"2022-02-04","cited_by_count":8,"area":"offlinerl"},{"id":"2203.06550","title":"Reinforced Imitative Graph Learning for Mobile User Profiling","created":"2022-03-13","cited_by_count":8,"area":null},{"id":"2107.05474","title":"Denoising User-aware Memory Network for Recommendation","created":"2021-07-12","cited_by_count":7,"area":null},{"id":"2308.12256","title":"Learning from Negative User Feedback and Measuring Responsiveness for Sequential Recommenders","created":"2023-08-23","cited_by_count":7,"area":null},{"id":"2205.11788","title":"Meta Policy Learning for Cold-Start Conversational Recommendation","created":"2022-05-24","cited_by_count":6,"area":null},{"id":"2110.07923","title":"Value Penalized Q-Learning for Recommender Systems","created":"2021-10-15","cited_by_count":4,"area":"offlinerl"},{"id":"2207.03029","title":"Multi-objective Optimization of Notifications Using Offline Reinforcement Learning","created":"2022-07-07","cited_by_count":4,"area":"offlinerl"},{"id":"2402.00390","title":"DNS-Rec: Data-aware Neural Architecture Search for Recommender Systems","created":"2024-02-01","cited_by_count":4,"area":null},{"id":"2412.04107","title":"Pre-train, Align, and Disentangle: Empowering Sequential Recommendation with Large Language Models","created":"2024-12-05","cited_by_count":4,"area":null},{"id":"2501.16125","title":"SampleLLM: Optimizing Tabular Data Synthesis in Recommendations","created":"2025-01-27","cited_by_count":4,"area":"synth"},{"id":"2601.04554","title":"Exploring Recommender System Evaluation: A Multi-Modal User Agent Framework for A/B Testing","created":"2026-01-08","cited_by_count":4,"area":"agents"},{"id":"2206.02000","title":"Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning","created":"2022-06-04","cited_by_count":3,"area":"offlinerl"},{"id":"2207.07790","title":"BCRLSP: An Offline Reinforcement Learning Framework for Sequential Targeted Promotion","created":"2022-07-16","cited_by_count":3,"area":"offlinerl"},{"id":"2403.17634","title":"Retentive Decision Transformer with Adaptive Masking for Reinforcement Learning based Recommendation Systems","created":"2024-03-26","cited_by_count":3,"area":"offlinerl"},{"id":"2505.12043","title":"MoL for LLMs: Dual-Loss Optimization to Enhance Domain Expertise While Preserving General Capabilities","created":"2025-05-17","cited_by_count":3,"area":null},{"id":"2506.16114","title":"GFlowGR: Fine-tuning Generative Recommendation Frameworks with Generative Flow Networks","created":"2025-06-19","cited_by_count":3,"area":"alignment"},{"id":"2204.04397","title":"Denoising Neural Network for News Recommendation with Positive and Negative Implicit Feedback","created":"2022-04-09","cited_by_count":2,"area":null},{"id":"2205.13248","title":"Constrained Reinforcement Learning for Short Video Recommendation","created":"2022-05-26","cited_by_count":2,"area":null},{"id":"2401.08959","title":"Towards Off-Policy Reinforcement Learning for Ranking Policies with Human Feedback","created":"2024-01-17","cited_by_count":2,"area":"deeprl"},{"id":"2403.04247","title":"UltraWiki: Ultra-fine-grained Entity Set Expansion with Negative Seed Entities","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2504.00460","title":"MetaLoRA: Tensor-Enhanced Adaptive Low-Rank Fine-tuning","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2506.12384","title":"Model Merging for Knowledge Editing","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2506.23090","title":"Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems","created":"2025-06-29","cited_by_count":2,"area":"offlinerl"},{"id":"2508.05709","title":"G-UBS: Towards Robust Understanding of Implicit Feedback via Group-Aware User Behavior Simulation","created":"2025-08-07","cited_by_count":2,"area":null},{"id":"2509.02017","title":"Empowering Large Language Model for Sequential Recommendation via Multimodal Embeddings and Semantic IDs","created":"2025-09-02","cited_by_count":2,"area":null},{"id":"2204.07543","title":"CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection","created":"2022-04-15","cited_by_count":1,"area":null},{"id":"2212.12517","title":"NARS vs. Reinforcement learning: ONA vs. Q-Learning","created":"2022-12-23","cited_by_count":1,"area":null},{"id":"2303.08115","title":"Human-Inspired Framework to Accelerate Reinforcement Learning","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2308.06965","title":"AutoAssign+: Automatic Shared Embedding Assignment in Streaming Recommendation","created":"2023-08-14","cited_by_count":1,"area":null},{"id":"2407.00082","title":"Adapting Job Recommendations to User Preference Drift with Behavioral-Semantic Fusion Learning","created":"2024-06-24","cited_by_count":1,"area":null},{"id":"2407.13091","title":"On Causally Disentangled State Representation Learning for Reinforcement Learning based Recommender Systems","created":"2024-07-18","cited_by_count":1,"area":"deeprl"},{"id":"2409.13175","title":"RPAF: A Reinforcement Prediction-Allocation Framework for Cache Allocation in Large-Scale Recommender Systems","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2506.14235","title":"A Multi-Expert Structural-Semantic Hybrid Framework for Unveiling Historical Patterns in Temporal Knowledge Graphs","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2511.19931","title":"LLM-EDT: Large Language Model Enhanced Cross-domain Sequential Recommendation with Dual-phase Training","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2601.08403","title":"Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs","created":"2026-01-13","cited_by_count":1,"area":"lr"},{"id":"2110.03039","title":"Optimized Recommender Systems with Deep Reinforcement Learning","created":"2021-10-06","cited_by_count":0,"area":null},{"id":"2110.15089","title":"D2RLIR : an improved and diversified ranking function in interactive recommendation systems based on deep reinforcement learning","created":"2021-10-28","cited_by_count":0,"area":null},{"id":"2202.09508","title":"Who Are the Best Adopters? User Selection Model for Free Trial Item Promotion","created":"2022-02-19","cited_by_count":0,"area":null},{"id":"2305.18820","title":"Robust Reinforcement Learning Objectives for Sequential Recommender Systems","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2308.11137","title":"Towards Validating Long-Term User Feedbacks in Interactive Recommendation Systems","created":"2023-08-22","cited_by_count":0,"area":null},{"id":"2507.23459","title":"KLAN: Kuaishou Landing-page Adaptive Navigator","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2510.04239","title":"Empowering Denoising Sequential Recommendation with Large Language Model Embeddings","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2607.28659","title":"Empowering Cross-Domain Sequential Recommendation with Hybrid Tokenization and Serial-Parallel Decoding","created":"2026-07-21","cited_by_count":0,"area":"inference"}],"next_cursor":null}