{"total":100,"rows":[{"id":"2402.17152","title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations","created":"2024-02-27","cited_by_count":188,"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":"2101.00494","title":"A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost","created":"2021-01-02","cited_by_count":40,"area":null},{"id":"2209.10117","title":"A Comprehensive Survey on Trustworthy Recommender Systems","created":"2022-09-21","cited_by_count":32,"area":null},{"id":"2106.06713","title":"AutoLoss: Automated Loss Function Search in Recommendations","created":"2021-06-12","cited_by_count":31,"area":null},{"id":"2110.04471","title":"Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning","created":"2021-10-09","cited_by_count":29,"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":"2102.08492","title":"Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments","created":"2021-02-16","cited_by_count":26,"area":null},{"id":"2302.03328","title":"Multi-Task Recommendations with Reinforcement Learning","created":"2023-02-07","cited_by_count":26,"area":null},{"id":"2403.00843","title":"Large Language Models are Learnable Planners for Long-Term Recommendation","created":"2024-02-29","cited_by_count":24,"area":null},{"id":"2109.04083","title":"User Tampering in Reinforcement Learning Recommender Systems","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2208.04560","title":"Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems","created":"2022-08-09","cited_by_count":22,"area":"offlinerl"},{"id":"2101.02634","title":"Reinforced Imitative Graph Representation Learning for Mobile User Profiling: An Adversarial Training Perspective","created":"2021-01-07","cited_by_count":21,"area":null},{"id":"2103.08057","title":"RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems","created":"2021-03-14","cited_by_count":21,"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":"2208.13663","title":"Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning","created":"2022-08-29","cited_by_count":21,"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":"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":"2112.11921","title":"Variational Quantum Soft Actor-Critic","created":"2021-12-20","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":"2111.11509","title":"Blockchain-based Recommender Systems: Applications, Challenges and Future Opportunities","created":"2021-11-22","cited_by_count":11,"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":"2308.11336","title":"On the Opportunities and Challenges of Offline Reinforcement Learning for Recommender Systems","created":"2023-08-22","cited_by_count":10,"area":"offlinerl"},{"id":"2103.05147","title":"Model-free Policy Learning with Reward Gradients","created":"2021-03-09","cited_by_count":9,"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":"2311.07127","title":"Multi-agent Attacks for Black-box Social Recommendations","created":"2023-11-13","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":"2203.15542","title":"Modeling Users' Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search","created":"2022-03-29","cited_by_count":8,"area":null},{"id":"2208.06263","title":"Probabilistic Rank and Reward: A Scalable Model for Slate Recommendation","created":"2022-08-10","cited_by_count":8,"area":null},{"id":"2302.03561","title":"Optimizing Audio Recommendations for the Long-Term: A Reinforcement Learning Perspective","created":"2023-02-07","cited_by_count":8,"area":null},{"id":"2209.15166","title":"Reward Shaping for User Satisfaction in a REINFORCE Recommender","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2106.00543","title":"MARL with General Utilities via Decentralized Shadow Reward Actor-Critic","created":"2021-05-29","cited_by_count":5,"area":null},{"id":"2104.02981","title":"Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation","created":"2021-04-07","cited_by_count":4,"area":"wm"},{"id":"2110.07923","title":"Value Penalized Q-Learning for Recommender Systems","created":"2021-10-15","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":"2402.13296","title":"Evolutionary Reinforcement Learning: A Systematic Review and Future Directions","created":"2024-02-20","cited_by_count":4,"area":"deeprl"},{"id":"2407.13163","title":"ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems","created":"2024-07-18","cited_by_count":4,"area":"alignment"},{"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":"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":"2409.17436","title":"Minimizing Live Experiments in Recommender Systems: User Simulation to Evaluate Preference Elicitation Policies","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2410.11833","title":"Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions","created":"2024-10-15","cited_by_count":3,"area":"deeprl"},{"id":"2411.11088","title":"An Investigation of Offline Reinforcement Learning in Factorisable Action Spaces","created":"2024-11-17","cited_by_count":3,"area":"offlinerl"},{"id":"2512.13726","title":"Time-Constrained Recommendations: Reinforcement Learning Strategies for E-Commerce","created":"2025-12-13","cited_by_count":3,"area":"deeprl"},{"id":"2603.08938","title":"AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2105.05473","title":"Interpretable performance analysis towards offline reinforcement learning: A dataset perspective","created":"2021-05-12","cited_by_count":2,"area":"offlinerl"},{"id":"2303.01671","title":"Tile Networks: Learning Optimal Geometric Layout for Whole-page Recommendation","created":"2023-03-03","cited_by_count":2,"area":null},{"id":"2307.07666","title":"Efficient Action Robust Reinforcement Learning with Probabilistic Policy Execution Uncertainty","created":"2023-07-15","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":"2401.09034","title":"UOEP: User-Oriented Exploration Policy for Enhancing Long-Term User Experiences in Recommender Systems","created":"2024-01-17","cited_by_count":2,"area":"deeprl"},{"id":"2408.04251","title":"Cooperative Multi-Agent Deep Reinforcement Learning in Content Ranking Optimization","created":"2024-08-08","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":"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":"2511.23271","title":"Learning a Single Token to Replace Long System Prompts in LLMs","created":"2025-11-28","cited_by_count":2,"area":null},{"id":"2202.00245","title":"Sequential Search with Off-Policy Reinforcement Learning","created":"2022-02-01","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":"2308.13246","title":"Model-free Reinforcement Learning with Stochastic Reward Stabilization for Recommender Systems","created":"2023-08-25","cited_by_count":1,"area":null},{"id":"2311.00859","title":"Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systems","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2401.06293","title":"MultiSlot ReRanker: A Generic Model-based Re-Ranking Framework in Recommendation Systems","created":"2024-01-11","cited_by_count":1,"area":null},{"id":"2402.14301","title":"GenSERP: Large Language Models for Whole Page Presentation","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2409.07416","title":"Hierarchical Reinforcement Learning for Temporal Abstraction of Listwise Recommendation","created":"2024-09-11","cited_by_count":1,"area":"deeprl"},{"id":"2501.02089","title":"On the Statistical Complexity for Offline and Low-Adaptive Reinforcement Learning with Structures","created":"2025-01-03","cited_by_count":1,"area":"offlinerl"},{"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":"2508.07746","title":"A Tutorial: An Intuitive Explanation of Offline Reinforcement Learning Theory","created":"2025-08-11","cited_by_count":1,"area":"offlinerl"},{"id":"2509.05292","title":"Deep Reinforcement Learning for Ranking Utility Tuning in the Ad Recommender System at Pinterest","created":"2025-09-05","cited_by_count":1,"area":"deeprl"},{"id":"2510.12815","title":"Energy-Guided Diffusion Sampling for Long-Term User Behavior Prediction in Reinforcement Learning-based Recommendation","created":"2025-10-09","cited_by_count":1,"area":"diffusion"},{"id":"2511.13293","title":"Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval","created":"2025-11-17","cited_by_count":1,"area":"agents"},{"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":"2108.02572","title":"SINGA-Easy: An Easy-to-Use Framework for MultiModal Analysis","created":"2021-08-03","cited_by_count":0,"area":null},{"id":"2108.02725","title":"VisualTextRank: Unsupervised Graph-based Content Extraction for Automating Ad Text to Image Search","created":"2021-08-05","cited_by_count":0,"area":null},{"id":"2109.05778","title":"Text is NOT Enough: Integrating Visual Impressions into Open-domain Dialogue Generation","created":"2021-09-13","cited_by_count":0,"area":null},{"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":"2112.05519","title":"A Validation Tool for Designing Reinforcement Learning Environments","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2112.05812","title":"Edge-Compatible Reinforcement Learning for Recommendations","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2202.02830","title":"Discovering Personalized Semantics for Soft Attributes in Recommender Systems using Concept Activation Vectors","created":"2022-02-06","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":"2203.11011","title":"Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks","created":"2022-03-08","cited_by_count":0,"area":null},{"id":"2205.08335","title":"Explanation-Guided Fairness Testing through Genetic Algorithm","created":"2022-05-16","cited_by_count":0,"area":null},{"id":"2207.14648","title":"Using Graph Neural Networks for Program Termination","created":"2022-07-28","cited_by_count":0,"area":null},{"id":"2303.09664","title":"Tribe or Not? Critical Inspection of Group Differences Using TribalGram","created":"2023-03-16","cited_by_count":0,"area":null},{"id":"2305.00254","title":"Semi-Infinitely Constrained Markov Decision Processes and Efficient Reinforcement Learning","created":"2023-04-29","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":"2503.07817","title":"Group Fairness in Multi-Task Reinforcement Learning","created":"2025-03-10","cited_by_count":0,"area":"deeprl"},{"id":"2507.23459","title":"KLAN: Kuaishou Landing-page Adaptive Navigator","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2508.21259","title":"Breaking the Cold-Start Barrier: Reinforcement Learning with Double and Dueling DQNs","created":"2025-08-28","cited_by_count":0,"area":"deeprl"},{"id":"2510.04239","title":"Empowering Denoising Sequential Recommendation with Large Language Model Embeddings","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2510.13792","title":"Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach","created":"2025-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2601.04441","title":"Improving and Accelerating Offline RL in Large Discrete Action Spaces with Structured Policy Initialization","created":"2026-01-07","cited_by_count":0,"area":"offlinerl"},{"id":"2605.16344","title":"A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems","created":"2026-05-08","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"},{"id":"2608.04421","title":"Generative Optimization for Incentivized Advertising with Global Level Constraints","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.28065","title":"Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning","created":"2026-08-28","cited_by_count":0,"area":"offlinerl"}],"next_cursor":null}