{"total":77,"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":"2405.16587","title":"Cost-Effective Online Multi-LLM Selection with Versatile Reward Models","created":"2024-05-26","cited_by_count":39,"area":"alignment"},{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2103.13929","title":"Multinomial Logit Contextual Bandits: Provable Optimality and Practicality","created":"2021-03-25","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":"2202.01454","title":"Deep Hierarchy in Bandits","created":"2022-02-03","cited_by_count":19,"area":null},{"id":"2110.14622","title":"Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization","created":"2021-10-27","cited_by_count":18,"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":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2306.00242","title":"Combinatorial Neural Bandits","created":"2023-05-31","cited_by_count":16,"area":null},{"id":"2208.14837","title":"Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent Arms","created":"2022-08-31","cited_by_count":15,"area":null},{"id":"2202.13227","title":"Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework","created":"2022-02-26","cited_by_count":11,"area":null},{"id":"2203.12577","title":"Minimax Regret for Cascading Bandits","created":"2022-03-23","cited_by_count":10,"area":null},{"id":"2503.01076","title":"Active Learning for Direct Preference Optimization","created":"2025-03-03","cited_by_count":10,"area":"alignment"},{"id":"2101.01086","title":"Be Greedy in Multi-Armed Bandits","created":"2021-01-04","cited_by_count":7,"area":null},{"id":"2202.08867","title":"Fast online inference for nonlinear contextual bandit based on Generative Adversarial Network","created":"2022-02-17","cited_by_count":7,"area":null},{"id":"2406.01386","title":"Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond","created":"2024-06-03","cited_by_count":7,"area":"deeprl"},{"id":"2102.05990","title":"Robust Generalization and Safe Query-Specialization in Counterfactual Learning to Rank","created":"2021-02-11","cited_by_count":6,"area":null},{"id":"2103.00368","title":"PairRank: Online Pairwise Learning to Rank by Divide-and-Conquer","created":"2021-02-28","cited_by_count":6,"area":null},{"id":"2205.04134","title":"Federated Multi-Armed Bandits Under Byzantine Attacks","created":"2022-05-09","cited_by_count":6,"area":null},{"id":"2211.02703","title":"Online Learning and Bandits with Queried Hints","created":"2022-11-04","cited_by_count":6,"area":null},{"id":"2305.17071","title":"Adversarial Attacks on Online Learning to Rank with Click Feedback","created":"2023-05-26","cited_by_count":6,"area":null},{"id":"2305.19158","title":"Competing for Shareable Arms in Multi-Player Multi-Armed Bandits","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2305.19218","title":"Adversarial Attacks on Online Learning to Rank with Stochastic Click Models","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2402.16312","title":"Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users","created":"2024-02-26","cited_by_count":6,"area":null},{"id":"2411.13029","title":"Probably Approximately Precision and Recall Learning","created":"2024-11-20","cited_by_count":5,"area":null},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2505.18828","title":"Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2111.04835","title":"Safe Data Collection for Offline and Online Policy Learning","created":"2021-11-08","cited_by_count":4,"area":null},{"id":"2401.08961","title":"Cascading Reinforcement Learning","created":"2024-01-17","cited_by_count":4,"area":"deeprl"},{"id":"2104.08615","title":"Conservative Contextual Combinatorial Cascading Bandit","created":"2021-04-17","cited_by_count":3,"area":null},{"id":"2112.05367","title":"Efficient Action Poisoning Attacks on Linear Contextual Bandits","created":"2021-12-10","cited_by_count":3,"area":null},{"id":"2210.08268","title":"Product Ranking for Revenue Maximization with Multiple Purchases","created":"2022-10-15","cited_by_count":3,"area":null},{"id":"2302.01543","title":"Multiplier Bootstrap-based Exploration","created":"2023-02-03","cited_by_count":3,"area":null},{"id":"2311.05975","title":"Sum-max Submodular Bandits","created":"2023-11-10","cited_by_count":3,"area":null},{"id":"2101.01572","title":"Sequential Choice Bandits with Feedback for Personalizing users' experience","created":"2021-01-05","cited_by_count":2,"area":null},{"id":"2110.02248","title":"Contextual Combinatorial Bandits with Changing Action Sets via Gaussian Processes","created":"2021-10-05","cited_by_count":2,"area":null},{"id":"2112.02165","title":"On Submodular Contextual Bandits","created":"2021-12-03","cited_by_count":2,"area":null},{"id":"2206.02593","title":"Pessimistic Off-Policy Optimization for Learning to Rank","created":"2022-06-06","cited_by_count":2,"area":null},{"id":"2207.05437","title":"Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model","created":"2022-07-12","cited_by_count":2,"area":null},{"id":"2210.09957","title":"Contextual bandits with concave rewards, and an application to fair ranking","created":"2022-10-18","cited_by_count":2,"area":null},{"id":"2310.05308","title":"Adversarial Attacks on Combinatorial Multi-Armed Bandits","created":"2023-10-08","cited_by_count":2,"area":null},{"id":"2504.07307","title":"Follow-the-Perturbed-Leader Approaches Best-of-Both-Worlds for the m-Set Semi-Bandit Problems","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2602.01658","title":"Efficient Adversarial Attacks on High-dimensional Offline Bandits","created":"2026-02-02","cited_by_count":2,"area":"alignment"},{"id":"2605.08287","title":"Multi-Armed Bandits With Best-Action Queries","created":"2026-05-08","cited_by_count":2,"area":null},{"id":"2103.04387","title":"CORe: Capitalizing On Rewards in Bandit Exploration","created":"2021-03-07","cited_by_count":1,"area":null},{"id":"2105.11126","title":"Cascading Bandit under Differential Privacy","created":"2021-05-24","cited_by_count":1,"area":null},{"id":"2109.02519","title":"Online Learning of Independent Cascade Models with Node-level Feedback","created":"2021-09-06","cited_by_count":1,"area":null},{"id":"2109.05899","title":"Online Learning of Optimally Diverse Rankings","created":"2021-09-13","cited_by_count":1,"area":null},{"id":"2111.00735","title":"Calibrating Explore-Exploit Trade-off for Fair Online Learning to Rank","created":"2021-11-01","cited_by_count":1,"area":null},{"id":"2201.06658","title":"Learning Neural Ranking Models Online from Implicit User Feedback","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2301.10651","title":"Overcoming Prior Misspecification in Online Learning to Rank","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2307.14138","title":"Piecewise-Stationary Combinatorial Semi-Bandit with Causally Related Rewards","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2311.07426","title":"Optimising Human-AI Collaboration by Learning Convincing Explanations","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2402.14013","title":"Misalignment, Learning, and Ranking: Harnessing Users Limited Attention","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2508.13981","title":"Multi-User Contextual Cascading Bandits for Personalized Recommendation","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2609.05820","title":"Online Learning with LLM Experts from Limited Feedback","created":"2026-09-05","cited_by_count":1,"area":null},{"id":"2106.03546","title":"On Learning to Rank Long Sequences with Contextual Bandits","created":"2021-06-07","cited_by_count":0,"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":"2207.11545","title":"Learning to Sell a Focal-ancillary Combination","created":"2022-07-23","cited_by_count":0,"area":null},{"id":"2208.01515","title":"UniRank: Unimodal Bandit Algorithm for Online Ranking","created":"2022-08-02","cited_by_count":0,"area":null},{"id":"2305.01202","title":"Exploration of Unranked Items in Safe Online Learning to Re-Rank","created":"2023-05-02","cited_by_count":0,"area":null},{"id":"2305.18333","title":"Ranking with Popularity Bias: User Welfare under Self-Amplification Dynamics","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2308.12680","title":"Master-slave Deep Architecture for Top-K Multi-armed Bandits with Non-linear Bandit Feedback and Diversity Constraints","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2403.15524","title":"PPA-Game: Characterizing and Learning Competitive Dynamics Among Online Content Creators","created":"2024-03-22","cited_by_count":0,"area":null},{"id":"2406.05017","title":"Adaptively Learning to Select-Rank in Online Platforms","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2508.06247","title":"Near-Optimal Regret for Efficient Stochastic Combinatorial Semi-Bandits","created":"2025-08-08","cited_by_count":0,"area":null},{"id":"2509.22855","title":"Observation-Free Attacks on Online Learning to Rank","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.03074","title":"Online Learning to Rank under Corruption: A Robust Cascading Bandits Approach","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2511.10938","title":"Cascading Bandits With Feedback","created":"2025-11-14","cited_by_count":0,"area":null},{"id":"2602.06565","title":"Learning to Allocate Resources with Censored Feedback","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.00567","title":"Learning to Attack: A Bandit Approach to Adversarial Context Poisoning","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2606.29221","title":"A Linear Matching Bandit Approach to Online Multi-Human Multi-Robot Teaming","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.15440","title":"Stochastic Reset Pathfinding: Path-Level Regret for Cascading Bandits over Graph Paths","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.11873","title":"DCM Bandits: Multiplayer Information Asymmetric Cascading Bandits for Multiple Clicks","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2610.05220","title":"Ranking Bandits for Carousel Interfaces with Observable Browsing Depth","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.12960","title":"DataCupid: Stable Matching Repair for Training Data Acquisition with Delayed Feedback","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}