{"total":65,"rows":[{"id":"2306.02552","title":"User Behavior Simulation with Large Language Model based Agents","created":"2023-06-05","cited_by_count":140,"area":"agents"},{"id":"2310.10108","title":"On Generative Agents in Recommendation","created":"2023-10-16","cited_by_count":90,"area":"agents"},{"id":"2305.07961","title":"Leveraging Large Language Models in Conversational Recommender Systems","created":"2023-05-13","cited_by_count":63,"area":null},{"id":"2412.16984","title":"LLM-Powered User Simulator for Recommender System","created":"2024-12-22","cited_by_count":39,"area":null},{"id":"2502.13187","title":"A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models","created":"2025-02-18","cited_by_count":38,"area":"deeprl"},{"id":"2205.11127","title":"Fairness in Recommender Systems: Research Landscape and Future Directions","created":"2022-05-23","cited_by_count":30,"area":null},{"id":"2107.10939","title":"What are you optimizing for? Aligning Recommender Systems with Human Values","created":"2021-07-22","cited_by_count":29,"area":"alignment"},{"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":"2201.12662","title":"Fair ranking: a critical review, challenges, and future directions","created":"2022-01-29","cited_by_count":21,"area":null},{"id":"2604.24977","title":"A Survey on LLM-based Conversational User Simulation","created":"2026-04-27","cited_by_count":18,"area":null},{"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":"2109.12509","title":"Deep Exploration for Recommendation Systems","created":"2021-09-26","cited_by_count":14,"area":null},{"id":"2307.15053","title":"On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-$n$ Recommendation","created":"2023-07-27","cited_by_count":13,"area":null},{"id":"2405.05736","title":"Optimal Baseline Corrections for Off-Policy Contextual Bandits","created":"2024-05-09","cited_by_count":13,"area":null},{"id":"2107.08959","title":"T-RECS: A Simulation Tool to Study the Societal Impact of Recommender Systems","created":"2021-07-19","cited_by_count":12,"area":null},{"id":"2102.12467","title":"No-Regret Algorithms for Private Gaussian Process Bandit Optimization","created":"2021-02-24","cited_by_count":11,"area":null},{"id":"2404.12366","title":"Accounting for AI and Users Shaping One Another: The Role of Mathematical Models","created":"2024-04-18","cited_by_count":11,"area":null},{"id":"2406.01631","title":"SUBER: An RL Environment with Simulated Human Behavior for Recommender Systems","created":"2024-06-01","cited_by_count":11,"area":null},{"id":"2306.07542","title":"A Versatile Multi-Agent Reinforcement Learning Benchmark for Inventory Management","created":"2023-06-13","cited_by_count":10,"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":"2208.13251","title":"A preprocessing perspective for quantum machine learning classification advantage using NISQ algorithms","created":"2022-08-28","cited_by_count":7,"area":null},{"id":"2109.06723","title":"Simulations in Recommender Systems: An industry perspective","created":"2021-09-14","cited_by_count":6,"area":null},{"id":"2202.08812","title":"Should I send this notification? Optimizing push notifications decision making by modeling the future","created":"2022-02-17","cited_by_count":6,"area":null},{"id":"2203.05952","title":"Balancing Consumer and Business Value of Recommender Systems: A Simulation-based Analysis","created":"2022-03-10","cited_by_count":6,"area":null},{"id":"2302.08617","title":"Quantum Computing Provides Exponential Regret Improvement in Episodic Reinforcement Learning","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2311.18206","title":"SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation","created":"2023-11-30","cited_by_count":6,"area":"offlinerl"},{"id":"2504.08754","title":"Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Action","created":"2025-03-28","cited_by_count":6,"area":"agents"},{"id":"2110.11073","title":"RL4RS: A Real-World Dataset for Reinforcement Learning based Recommender System","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2206.11338","title":"Synthetic Data-Based Simulators for Recommender Systems: A Survey","created":"2022-06-22","cited_by_count":5,"area":null},{"id":"2405.13362","title":"Lusifer: LLM-based User SImulated Feedback Environment for online Recommender systems","created":"2024-05-22","cited_by_count":5,"area":null},{"id":"2108.11068","title":"Understanding Longitudinal Dynamics of Recommender Systems with Agent-Based Modeling and Simulation","created":"2021-08-25","cited_by_count":4,"area":null},{"id":"2206.08851","title":"SMPL: Simulated Industrial Manufacturing and Process Control Learning Environments","created":"2022-06-17","cited_by_count":4,"area":null},{"id":"2309.01026","title":"Zero-Shot Recommendations with Pre-Trained Large Language Models for Multimodal Nudging","created":"2023-09-02","cited_by_count":4,"area":null},{"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":"2107.07693","title":"Imitate TheWorld: A Search Engine Simulation Platform","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2201.07681","title":"Learning to Rank For Push Notifications Using Pairwise Expected Regret","created":"2022-01-19","cited_by_count":3,"area":null},{"id":"2205.15379","title":"Truly Deterministic Policy Optimization","created":"2022-05-30","cited_by_count":3,"area":null},{"id":"2211.11869","title":"Examining Policy Entropy of Reinforcement Learning Agents for Personalization Tasks","created":"2022-11-21","cited_by_count":3,"area":null},{"id":"2403.17533","title":"BVR Gym: A Reinforcement Learning Environment for Beyond-Visual-Range Air Combat","created":"2024-03-26","cited_by_count":3,"area":"deeprl"},{"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":"2106.00589","title":"Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Reinforcement Learning","created":"2021-06-01","cited_by_count":2,"area":null},{"id":"2112.11022","title":"Synthetic Data and Simulators for Recommendation Systems: Current State and Future Directions","created":"2021-12-21","cited_by_count":2,"area":null},{"id":"2209.04147","title":"Extending Open Bandit Pipeline to Simulate Industry Challenges","created":"2022-09-09","cited_by_count":2,"area":null},{"id":"2209.08642","title":"Offline Evaluation of Reward-Optimizing Recommender Systems: The Case of Simulation","created":"2022-09-18","cited_by_count":2,"area":null},{"id":"2408.16032","title":"An Extremely Data-efficient and Generative LLM-based Reinforcement Learning Agent for Recommenders","created":"2024-08-28","cited_by_count":2,"area":"agents"},{"id":"2107.08598","title":"Learning-To-Ensemble by Contextual Rank Aggregation in E-Commerce","created":"2021-07-19","cited_by_count":1,"area":null},{"id":"2210.10309","title":"Multi-Objective Recommender Systems: Survey and Challenges","created":"2022-10-19","cited_by_count":1,"area":null},{"id":"2210.10631","title":"Simulated Contextual Bandits for Personalization Tasks from Recommendation Datasets","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2305.14103","title":"Simulating News Recommendation Ecosystem for Fun and Profit","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2409.20055","title":"Neural Click Models for Recommender Systems","created":"2024-09-30","cited_by_count":1,"area":null},{"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":"2511.04541","title":"Offline A/B Testing of Slate Recommendation Systems with LLMs: Reducing the Dependency on Pre-Collected User Interaction Data","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2608.01204","title":"ShiJianBench: From Dialogue to Decision for Long-Horizon Evaluation of Investment Advisors","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2102.00333","title":"Deep Reinforcement Learning-Based Product Recommender for Online Advertising","created":"2021-01-30","cited_by_count":0,"area":null},{"id":"2203.10629","title":"Explicit User Manipulation in Reinforcement Learning Based Recommender Systems","created":"2022-03-20","cited_by_count":0,"area":null},{"id":"2209.01876","title":"SlateFree: a Model-Free Decomposition for Reinforcement Learning with Slate Actions","created":"2022-09-05","cited_by_count":0,"area":null},{"id":"2210.05662","title":"Understanding or Manipulation: Rethinking Online Performance Gains of Modern Recommender Systems","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2402.15819","title":"Debiased Model-based Interactive Recommendation","created":"2024-02-24","cited_by_count":0,"area":null},{"id":"2407.15476","title":"MODRL-TA:A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search","created":"2024-07-22","cited_by_count":0,"area":"deeprl"},{"id":"2408.04531","title":"AExGym: Benchmarks and Environments for Adaptive Experimentation","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2507.18756","title":"Exploitation Over Exploration: Unmasking the Bias in Linear Bandit Recommender Offline Evaluation","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2508.07914","title":"Meta Off-Policy Estimation","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2605.18805","title":"RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents","created":"2026-05-11","cited_by_count":0,"area":"agents"}],"next_cursor":null}