{"total":73,"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":"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":"2507.04632","title":"Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?","created":"2025-07-07","cited_by_count":52,"area":"lr"},{"id":"2509.21880","title":"No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping","created":"2025-09-26","cited_by_count":50,"area":"lr"},{"id":"2509.21009","title":"RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training","created":"2025-09-25","cited_by_count":35,"area":"lr"},{"id":"2509.13232","title":"Single-stream Policy Optimization","created":"2025-09-16","cited_by_count":28,"area":"lr"},{"id":"2510.00977","title":"It Takes Two: Your GRPO Is Secretly DPO","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2510.04996","title":"Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives","created":"2025-10-06","cited_by_count":25,"area":"lr"},{"id":"2509.01321","title":"Towards High Data Efficiency in Reinforcement Learning with Verifiable Reward","created":"2025-09-01","cited_by_count":19,"area":"lr"},{"id":"2602.08354","title":"Does Your Reasoning Model Implicitly Know When to Stop Thinking?","created":"2026-02-09","cited_by_count":19,"area":"lr"},{"id":"2510.06672","title":"XRPO: Pushing the limits of GRPO with Targeted Exploration and Exploitation","created":"2025-10-08","cited_by_count":18,"area":"lr"},{"id":"2602.01970","title":"Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models","created":"2026-02-02","cited_by_count":14,"area":"lr"},{"id":"2509.23232","title":"SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts","created":"2025-09-27","cited_by_count":12,"area":"lr"},{"id":"2510.19225","title":"RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs","created":"2025-10-22","cited_by_count":11,"area":"lr"},{"id":"2602.08499","title":"Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2603.10887","title":"Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models","created":"2026-03-11","cited_by_count":11,"area":"lr"},{"id":"2508.13023","title":"G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance","created":"2025-08-18","cited_by_count":10,"area":"lr"},{"id":"2510.05251","title":"Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning","created":"2025-10-06","cited_by_count":10,"area":"lr"},{"id":"2603.24840","title":"Prune as You Generate: Online Rollout Pruning for Faster and Better RLVR","created":"2026-03-25","cited_by_count":10,"area":"lr"},{"id":"2606.15455","title":"Understanding Diversity Collapse in RLVR via the Lens of Overtraining","created":"2026-06-13","cited_by_count":10,"area":"lr"},{"id":"2509.21792","title":"FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft Learning","created":"2025-09-26","cited_by_count":9,"area":"lr"},{"id":"2510.01459","title":"LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning","created":"2025-10-01","cited_by_count":9,"area":"lr"},{"id":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","cited_by_count":9,"area":"lr"},{"id":"2606.01281","title":"RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning","created":"2026-05-31","cited_by_count":9,"area":"lr"},{"id":"2512.18215","title":"Stable and Efficient Single-Rollout RL for Multimodal Reasoning","created":"2025-12-20","cited_by_count":8,"area":"lr"},{"id":"2602.13953","title":"QuRL: Efficient Reinforcement Learning with Quantized Rollout","created":"2026-02-15","cited_by_count":8,"area":"lr"},{"id":"2603.21177","title":"Prompt replay: speeding up grpo with on-policy reuse of high-signal prompts","created":"2026-03-22","cited_by_count":8,"area":"lr"},{"id":"2511.00794","title":"Efficient Reinforcement Learning for Large Language Models with Intrinsic Exploration","created":"2025-11-02","cited_by_count":7,"area":"lr"},{"id":"2511.04800","title":"Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models","created":"2025-11-06","cited_by_count":7,"area":"lr"},{"id":"2601.09083","title":"SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache","created":"2026-01-14","cited_by_count":5,"area":"lr"},{"id":"2602.06107","title":"Jackpot: Optimal Budgeted Rejection Sampling for Extreme Actor-Policy Mismatch Reinforcement Learning","created":"2026-02-05","cited_by_count":5,"area":"lr"},{"id":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2510.04072","title":"Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning","created":"2025-10-05","cited_by_count":4,"area":"lr"},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2601.22448","title":"HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning","created":"2026-01-30","cited_by_count":4,"area":"lr"},{"id":"2601.23058","title":"From Absolute to Relative: Rethinking Reward Shaping in Group-Based Reinforcement Learning","created":"2026-01-30","cited_by_count":4,"area":"lr"},{"id":"2512.15274","title":"Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning","created":"2025-12-17","cited_by_count":3,"area":"lr"},{"id":"2602.07830","title":"Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning","created":"2026-02-08","cited_by_count":3,"area":"lr"},{"id":"2605.08873","title":"CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2606.10709","title":"Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Training","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2603.18444","title":"Discounted Beta-Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards","created":"2026-03-19","cited_by_count":2,"area":"lr"},{"id":"2605.05802","title":"Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2605.09188","title":"DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2605.28295","title":"Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.06080","title":"On Advantage Estimates for Max@K Policy Gradients","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2606.06828","title":"AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO","created":"2026-06-05","cited_by_count":2,"area":"lr"},{"id":"2607.27610","title":"Kalman Meets Curriculum: Efficient Dynamic Prompt Selection for Adaptive RL Finetuning","created":"2026-07-30","cited_by_count":2,"area":"lr"},{"id":"2608.09217","title":"Beyond Solvability: Task Learnability as a Static Prior for LLM RL Post-Training","created":"2026-08-10","cited_by_count":2,"area":"lr"},{"id":"2608.26070","title":"Prefix Sliding for efficient test-time scaling","created":"2026-08-26","cited_by_count":2,"area":"lr"},{"id":"2609.08650","title":"Difficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR","created":"2026-09-08","cited_by_count":2,"area":"lr"},{"id":"2609.09075","title":"ThinkPrior: Zero-Rollout Difficulty Priors for Cold-Start Prompt Selection in RLVR","created":"2026-09-08","cited_by_count":2,"area":"lr"},{"id":"2511.22891","title":"ORION: Teaching Language Models to Reason Efficiently in the Language of Thought","created":"2025-11-28","cited_by_count":1,"area":"lr"},{"id":"2601.22432","title":"ReNCE: Learning to Reason by Noise Contrastive Estimation","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.12642","title":"Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR","created":"2026-02-13","cited_by_count":1,"area":"lr"},{"id":"2602.16839","title":"Training Large Reasoning Models Efficiently via Progressive Thought Encoding","created":"2026-02-18","cited_by_count":1,"area":"lr"},{"id":"2604.16972","title":"MCPO: Mastery-Consolidated Policy Optimization for Large Reasoning Models","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2608.11368","title":"PAIR: Pairwise-Aware Inclusion Reweighting for Adaptive Rollout Allocation in RLVR","created":"2026-08-11","cited_by_count":1,"area":"lr"},{"id":"2601.04731","title":"Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models","created":"2026-01-08","cited_by_count":0,"area":"lr"},{"id":"2601.21244","title":"Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2604.17312","title":"A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2605.06755","title":"Gradient Extrapolation-Based Policy Optimization","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.16154","title":"Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking","created":"2026-05-15","cited_by_count":0,"area":"lr"},{"id":"2605.19425","title":"When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2606.08346","title":"CATPO: Critique-Augmented Tree Policy Optimization","created":"2026-06-06","cited_by_count":0,"area":"lr"},{"id":"2606.11634","title":"Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.19750","title":"Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2606.28166","title":"Tandem Reinforcement Learning with Verifiable Rewards","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2609.34975","title":"Teach to Learn: Hint Annealing for Self-improving LLM Reasoning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.34990","title":"MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.35426","title":"Frontier Learning: Training LLM Reasoners at the Edge of Capability","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36552","title":"SERA: Scale-Equalized Rollout Allocation for Maximum Likelihood Reinforcement Learning","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38018","title":"Prompts Live on an Arc: Gaussian Curricula in Fisher--Rao Coordinates for Rollout-Efficient GRPO","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.02039","title":"CARM: Cancellation-Aware Response Masking for LLM Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}