{"total":23,"rows":[{"id":"2510.18874","title":"Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting","created":"2025-10-21","cited_by_count":94,"area":null},{"id":"2505.11711","title":"Reinforcement Learning Finetunes Small Subnetworks in Large Language Models","created":"2025-05-16","cited_by_count":49,"area":null},{"id":"2510.01135","title":"Prompt Curriculum Learning for Efficient LLM Post-Training","created":"2025-10-01","cited_by_count":45,"area":null},{"id":"2603.12228","title":"Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights","created":"2026-03-12","cited_by_count":28,"area":null},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"id":"2508.20697","title":"Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning","created":"2025-08-28","cited_by_count":8,"area":null},{"id":"2509.08604","title":"Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications","created":"2025-09-10","cited_by_count":5,"area":null},{"id":"2510.17793","title":"Foundational Automatic Evaluators: Scaling Multi-Task Generative Evaluator Training for Reasoning-Centric Domains","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2601.15609","title":"When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards","created":"2026-01-22","cited_by_count":4,"area":null},{"id":"2603.27448","title":"GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedback","created":"2026-03-28","cited_by_count":3,"area":null},{"id":"2604.25477","title":"DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing","created":"2026-04-28","cited_by_count":3,"area":null},{"id":"2607.07646","title":"RL Post-Training Builds Compositional Reasoning Strategies","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2511.18055","title":"IE-Critic-R1: Advancing the Explanatory Measurement of Text-Driven Image Editing for Human Perception Alignment","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2602.10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2605.07244","title":"Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2606.18307","title":"DRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2605.30201","title":"HPO: Hysteretic Policy Optimization for Stable and Efficient Training under Sparse-Reward Regime","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.00257","title":"ARCA: Adapter-Residual Credit Assignment When Token Signals Degenerate","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.11189","title":"A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2608.14212","title":"APTER: Adaptive Post-Training with Expert-Grounded Rubrics","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.17162","title":"OraclePhys: A Systematic Framework for LLM Fine-Tuning on Structural Mechanics","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2610.15782","title":"Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}