{"total":41,"rows":[{"id":"2505.24298","title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","created":"2025-05-30","cited_by_count":250,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","created":"2025-08-15","cited_by_count":91,"area":"lr"},{"id":"2510.01161","title":"Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?","created":"2025-10-01","cited_by_count":53,"area":"lr"},{"id":"2510.02245","title":"ExGRPO: Learning to Reason from Experience","created":"2025-10-02","cited_by_count":53,"area":"lr"},{"id":"2509.19128","title":"PipelineRL: Faster On-policy Reinforcement Learning for Long Sequence Generation","created":"2025-09-23","cited_by_count":32,"area":"lr"},{"id":"2506.20520","title":"Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards","created":"2025-06-25","cited_by_count":29,"area":"lr"},{"id":"2510.00194","title":"GRPO-$\\lambda$: Credit Assignment improves LLM Reasoning","created":"2025-09-30","cited_by_count":23,"area":"lr"},{"id":"2506.13923","title":"Adaptive Guidance Accelerates Reinforcement Learning of Reasoning Models","created":"2025-06-16","cited_by_count":18,"area":"lr"},{"id":"2507.06892","title":"Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2510.08696","title":"Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2602.19362","title":"LLMs Can Learn to Reason Via Off-Policy RL","created":"2026-02-22","cited_by_count":10,"area":"lr"},{"id":"2511.20718","title":"Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization","created":"2025-11-25","cited_by_count":9,"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":"2509.21282","title":"It's Not You, It's Clipping: A Soft Trust-Region via Probability Smoothing for LLM RL","created":"2025-09-25","cited_by_count":7,"area":"lr"},{"id":"2601.22718","title":"A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization","created":"2026-01-30","cited_by_count":7,"area":"lr"},{"id":"2605.17570","title":"How Off-Policy Can GRPO Be? Mu-GRPO for Efficient LLM Reinforcement Learning","created":"2026-05-17","cited_by_count":7,"area":"lr"},{"id":"2505.14403","title":"Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning","created":"2025-05-20","cited_by_count":6,"area":"lr"},{"id":"2507.08068","title":"Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions","created":"2025-07-10","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":"2506.20241","title":"Enhancing Large Language Models through Structured Reasoning","created":"2025-06-25","cited_by_count":5,"area":"lr"},{"id":"2510.00819","title":"Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"id":"2510.05825","title":"Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling","created":"2025-10-07","cited_by_count":4,"area":"lr"},{"id":"2602.11128","title":"Asymmetric Prompt Weighting for Reinforcement Learning with Verifiable Rewards","created":"2026-02-11","cited_by_count":4,"area":"lr"},{"id":"2510.23486","title":"Learning to Reason Efficiently with Discounted Reinforcement Learning","created":"2025-10-27","cited_by_count":3,"area":"lr"},{"id":"2511.05589","title":"CoPRIS: Efficient and Stable Reinforcement Learning via Concurrency-Controlled Partial Rollout with Importance Sampling","created":"2025-11-05","cited_by_count":3,"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":"2604.16918","title":"Freshness-Aware Prioritized Experience Replay for LLM/VLM Reinforcement Learning","created":"2026-04-18","cited_by_count":3,"area":"lr"},{"id":"2609.20807","title":"Score Centering Stabilizes Off-policy Reinforcement Learning","created":"2026-09-17","cited_by_count":3,"area":"lr"},{"id":"2509.04501","title":"Understanding Reinforcement Learning for Model Training, and future directions with GRAPE","created":"2025-09-02","cited_by_count":2,"area":"lr"},{"id":"2606.04560","title":"Rollout-Level Advantage-Prioritized Experience Replay for GRPO","created":"2026-06-03","cited_by_count":2,"area":"lr"},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2510.23868","title":"GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA","created":"2025-10-27","cited_by_count":1,"area":"lr"},{"id":"2607.16205","title":"It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2508.10123","title":"Nested-ReFT: Efficient Reinforcement Learning for Large Language Model Fine-Tuning via Off-Policy Rollouts","created":"2025-08-13","cited_by_count":0,"area":"lr"},{"id":"2605.15012","title":"Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2606.22570","title":"What are Key Factors for Updates in RL for LLM Reasoning?","created":"2026-06-21","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":"2609.33970","title":"On the Token Value Inequality in Efficient Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.01896","title":"Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}