{"total":17,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2512.21852","title":"A Comedy of Estimators: On KL Regularization in RL Training of LLMs","created":"2025-12-26","cited_by_count":18,"area":"lr"},{"id":"2602.04663","title":"Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design","created":"2026-02-04","cited_by_count":17,"area":"lr"},{"id":"2601.10201","title":"Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization","created":"2026-01-15","cited_by_count":12,"area":"lr"},{"id":"2605.19282","title":"Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"id":"2606.01039","title":"OPD+: Rethinking the Advantage Design for On-Policy Distillation","created":"2026-05-31","cited_by_count":8,"area":"lr"},{"id":"2606.04036","title":"Self-Distilled Policy Gradient","created":"2026-06-02","cited_by_count":8,"area":"lr"},{"id":"2508.04848","title":"Large Language Models Reasoning Abilities Under Non-Ideal Conditions After RL-Fine-Tuning","created":"2025-08-06","cited_by_count":7,"area":"lr"},{"id":"2506.08672","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","created":"2025-06-10","cited_by_count":6,"area":"lr"},{"id":"2601.03320","title":"Ratio-Variance Regularized Policy Optimization for Efficient LLM Fine-tuning","created":"2026-01-06","cited_by_count":6,"area":"lr"},{"id":"2602.04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2602.04620","title":"QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2605.18864","title":"SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs","created":"2026-05-15","cited_by_count":3,"area":"lr"},{"id":"2604.23333","title":"Process Supervision of Confidence Margin for Calibrated LLM Reasoning","created":"2026-04-25","cited_by_count":2,"area":"lr"},{"id":"2602.05494","title":"A Unified Framework for Rethinking Policy Divergence Measures in GRPO","created":"2026-02-05","cited_by_count":0,"area":"lr"},{"id":"2607.06987","title":"UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma","created":"2026-07-08","cited_by_count":0,"area":"lr"},{"id":"2609.15987","title":"Bellman Policy Optimization","created":"2026-09-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}