{"total":3,"rows":[{"id":"2509.17105","title":"GRPOformer: Advancing Hyperparameter Optimization via Group Relative Policy Optimization","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2606.29526","title":"The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning","created":"2026-06-28","cited_by_count":1,"area":null}],"next_cursor":null}