{"total":94,"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":"2310.09233","title":"AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems","created":"2023-10-13","cited_by_count":116,"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":"2409.20296","title":"PersonalLLM: Tailoring LLMs to Individual Preferences","created":"2024-09-30","cited_by_count":60,"area":"alignment"},{"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":"2205.13619","title":"Fairness in Recommendation: Foundations, Methods and Applications","created":"2022-05-26","cited_by_count":27,"area":null},{"id":"2302.03328","title":"Multi-Task Recommendations with Reinforcement Learning","created":"2023-02-07","cited_by_count":26,"area":null},{"id":"2503.16734","title":"Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models","created":"2025-03-20","cited_by_count":26,"area":"mllm"},{"id":"2206.03944","title":"Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-implementation Guidelines","created":"2022-06-08","cited_by_count":22,"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":"2101.04526","title":"Measuring Recommender System Effects with Simulated Users","created":"2021-01-12","cited_by_count":20,"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":"2504.16420","title":"A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms","created":"2025-04-23","cited_by_count":17,"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":"2110.06539","title":"On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning","created":"2021-10-13","cited_by_count":14,"area":"offlinerl"},{"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":"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":"2602.16938","title":"ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders","created":"2026-02-18","cited_by_count":12,"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":"2505.07581","title":"YuLan-OneSim: Towards the Next Generation of Social Simulator with Large Language Models","created":"2025-05-12","cited_by_count":11,"area":"wm"},{"id":"2102.13302","title":"Variation Control and Evaluation for Generative SlateRecommendations","created":"2021-02-26","cited_by_count":10,"area":null},{"id":"2105.02377","title":"Towards Content Provider Aware Recommender Systems: A Simulation Study on the Interplay between User and Provider Utilities","created":"2021-05-06","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":"2604.08362","title":"Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces","created":"2026-04-09","cited_by_count":9,"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":"2506.12078","title":"Modeling Earth-Scale Human-Like Societies with One Billion Agents","created":"2025-06-07","cited_by_count":8,"area":"agents"},{"id":"2109.06723","title":"Simulations in Recommender Systems: An industry perspective","created":"2021-09-14","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":"2406.13130","title":"Advancing Retail Data Science: Comprehensive Evaluation of Synthetic Data","created":"2024-06-19","cited_by_count":6,"area":null},{"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":"2305.04832","title":"Sim2Rec: A Simulator-based Decision-making Approach to Optimize Real-World Long-term User Engagement in Sequential Recommender Systems","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2310.03984","title":"AURO: Reinforcement Learning for Adaptive User Retention Optimization in Recommender Systems","created":"2023-10-06","cited_by_count":5,"area":null},{"id":"2312.14095","title":"RetailSynth: Synthetic Data Generation for Retail AI Systems Evaluation","created":"2023-12-21","cited_by_count":5,"area":null},{"id":"2505.16429","title":"Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems","created":"2025-05-22","cited_by_count":5,"area":"agents"},{"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":"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":"2402.15957","title":"DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning","created":"2024-02-25","cited_by_count":4,"area":"deeprl"},{"id":"2405.10469","title":"Simulation-Based Benchmarking of Reinforcement Learning Agents for Personalized Retail Promotions","created":"2024-05-16","cited_by_count":4,"area":"deeprl"},{"id":"2409.04744","title":"Reward Guidance for Reinforcement Learning Tasks Based on Large Language Models: The LMGT Framework","created":"2024-09-07","cited_by_count":4,"area":null},{"id":"2412.14741","title":"Active Inference and Human--Computer Interaction","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2503.22726","title":"InfoBid: A Simulation Framework for Studying Information Disclosure in Auctions with Large Language Model-based Agents","created":"2025-03-26","cited_by_count":4,"area":"agents"},{"id":"2508.18142","title":"Mirroring Users: Towards Building Preference-aligned User Simulator with User Feedback in Recommendation","created":"2025-08-25","cited_by_count":4,"area":"alignment"},{"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":"2211.11869","title":"Examining Policy Entropy of Reinforcement Learning Agents for Personalization Tasks","created":"2022-11-21","cited_by_count":3,"area":null},{"id":"2211.13585","title":"Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement","created":"2022-11-24","cited_by_count":3,"area":null},{"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":"2505.21154","title":"GGBond: Growing Graph-Based AI-Agent Society for Socially-Aware Recommender Simulation","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2508.00201","title":"RecoMind: A Reinforcement Learning Framework for Optimizing In-Session User Satisfaction in Recommendation Systems","created":"2025-07-31","cited_by_count":3,"area":"deeprl"},{"id":"2109.00177","title":"Problem Learning: Towards the Free Will of Machines","created":"2021-09-01","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":"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":"2111.03340","title":"FINN.no Slates Dataset: A new Sequential Dataset Logging Interactions, allViewed Items and Click Responses/No-Click for Recommender Systems Research","created":"2021-11-05","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":"2304.09088","title":"A Field Test of Bandit Algorithms for Recommendations: Understanding the Validity of Assumptions on Human Preferences in Multi-armed Bandits","created":"2023-04-16","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":"2308.06965","title":"AutoAssign+: Automatic Shared Embedding Assignment in Streaming Recommendation","created":"2023-08-14","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":"2409.08752","title":"A Hybrid Meta-Learning and Multi-Armed Bandit Approach for Context-Specific Multi-Objective Recommendation Optimization","created":"2024-09-13","cited_by_count":1,"area":null},{"id":"2409.14872","title":"FedSlate:A Federated Deep Reinforcement Learning Recommender System","created":"2024-09-23","cited_by_count":1,"area":"deeprl"},{"id":"2410.21892","title":"Guided Diffusion-based Counterfactual Augmentation for Robust Session-based Recommendation","created":"2024-10-29","cited_by_count":1,"area":"diffusion"},{"id":"2503.03606","title":"Decoupled Recommender Systems: Exploring Alternative Recommender Ecosystem Designs","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2504.16472","title":"Harden and Catch for Just-in-Time Assured LLM-Based Software Testing: Open Research Challenges","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2603.11399","title":"Entropy Guided Diversification and Preference Elicitation in Agentic Recommendation Systems","created":"2026-03-12","cited_by_count":1,"area":"agents"},{"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":"2108.01455","title":"FEBR: Expert-Based Recommendation Framework for beneficial and personalized content","created":"2021-07-17","cited_by_count":0,"area":null},{"id":"2109.07835","title":"Incentives in Two-sided Matching Markets with Prediction-enhanced Preference-formation","created":"2021-09-16","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":"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":"2211.06365","title":"Situating Recommender Systems in Practice: Towards Inductive Learning and Incremental Updates","created":"2022-11-11","cited_by_count":0,"area":null},{"id":"2303.01954","title":"Synthetic Data Generator for Adaptive Interventions in Global Health","created":"2023-03-03","cited_by_count":0,"area":null},{"id":"2310.17915","title":"Lifting the Veil: Unlocking the Power of Depth in Q-learning","created":"2023-10-27","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":"2409.12396","title":"ARTAI: An Evaluation Platform to Assess Societal Risk of Recommender Algorithms","created":"2024-09-19","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":"2601.22547","title":"PersonaAct: Simulating Short-Video Users with Personalized Agents for Counterfactual Filter Bubble Auditing","created":"2026-01-30","cited_by_count":0,"area":"agents"},{"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"},{"id":"2605.28810","title":"Affective Music Recommendation: A Rollout-Based World Model for Offline Preference Optimization","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2609.28405","title":"Learning Collective Dynamics with Differentiable Gaussian Representations","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.30711","title":"Recommendation World Models for Future-State Control","created":"2026-09-25","cited_by_count":0,"area":"wm"},{"id":"2610.00758","title":"Scalable Multi-Task Inverse Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"offlinerl"},{"id":"2610.09296","title":"The AI Evaluation Ecosystem","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.13617","title":"Training User Simulators with Latent Intrinsic Feedback","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13989","title":"PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems","created":"2026-09-26","cited_by_count":0,"area":"agents"}],"next_cursor":null}