{"total":19,"rows":[{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185,"area":null},{"id":"2401.06081","title":"Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint","created":"2024-01-11","cited_by_count":39,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2502.09053","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","created":"2025-02-13","cited_by_count":16,"area":null},{"id":"2411.03651","title":"Policy Aggregation","created":"2024-11-06","cited_by_count":8,"area":null},{"id":"2506.03464","title":"From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications","created":"2025-06-04","cited_by_count":8,"area":null},{"id":"2405.09794","title":"Human-AI Safety: A Descendant of Generative AI and Control Systems Safety","created":"2024-05-16","cited_by_count":7,"area":null},{"id":"2406.17312","title":"Not All Preference Pairs Are Created Equal: A Recipe for Annotation-Efficient Iterative Preference Learning","created":"2024-06-25","cited_by_count":7,"area":null},{"id":"2502.09780","title":"Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games","created":"2025-02-13","cited_by_count":3,"area":null},{"id":"2502.10505","title":"Preference learning made easy: Everything should be understood through win rate","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2501.06248","title":"Utility-inspired Reward Transformations Improve Reinforcement Learning Training of Language Models","created":"2025-01-08","cited_by_count":2,"area":null},{"id":"2503.05306","title":"Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning","created":"2025-03-07","cited_by_count":2,"area":null},{"id":"2510.11691","title":"Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games","created":"2025-10-13","cited_by_count":2,"area":null},{"id":"2502.01127","title":"The Battling Influencers Game: Nash Equilibria Structure of a Potential Game and Implications to Value Alignment","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2503.10215","title":"Adaptive Preference Aggregation","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2602.11857","title":"Scale-Invariant Fast Convergence in Games","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2602.21297","title":"Robust AI Evaluation through Maximal Lotteries","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2605.13806","title":"Min-Max Optimization Requires Exponentially Many Queries","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2602.19041","title":"Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning","created":"2026-02-22","cited_by_count":0,"area":null}],"next_cursor":null}