{"total":281,"rows":[{"id":"2508.05004","title":"R-Zero: Self-Evolving Reasoning LLM from Zero Data","created":"2025-08-07","cited_by_count":228,"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":"2603.07079","title":"Entropy-Aware On-Policy Distillation of Language Models","created":"2026-03-07","cited_by_count":175,"area":"distill"},{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172,"area":"lr"},{"id":"2508.10751","title":"Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models","created":"2025-08-14","cited_by_count":138,"area":"lr"},{"id":"2604.03128","title":"Self-Distilled RLVR","created":"2026-04-03","cited_by_count":131,"area":"distill"},{"id":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111,"area":"lr"},{"id":"2509.06941","title":"Outcome-based Exploration for LLM Reasoning","created":"2025-09-08","cited_by_count":83,"area":"lr"},{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2508.16949","title":"Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning","created":"2025-08-23","cited_by_count":63,"area":"lr"},{"id":"2508.14029","title":"Beyond Pass@1: Self-Play with Variational Problem Synthesis Sustains RLVR","created":"2025-08-19","cited_by_count":54,"area":"lr"},{"id":"2508.20722","title":"rStar2-Agent: Agentic Reasoning Technical Report","created":"2025-08-28","cited_by_count":54,"area":"lr"},{"id":"2510.10150","title":"Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective","created":"2025-10-11","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":"2510.18927","title":"BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping","created":"2025-10-21","cited_by_count":47,"area":null},{"id":"2511.15661","title":"VisPlay: Self-Evolving Vision-Language Models from Images","created":"2025-11-19","cited_by_count":47,"area":"lr"},{"id":"2509.09265","title":"Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents","created":"2025-09-11","cited_by_count":46,"area":"agents"},{"id":"2509.03646","title":"Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning","created":"2025-09-03","cited_by_count":42,"area":"lr"},{"id":"2507.21848","title":"EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity","created":"2025-07-29","cited_by_count":41,"area":"lr"},{"id":"2509.15207","title":"FlowRL: Matching Reward Distributions for LLM Reasoning","created":"2025-09-18","cited_by_count":40,"area":"lr"},{"id":"2510.14545","title":"Agentic Entropy-Balanced Policy Optimization","created":"2025-10-16","cited_by_count":40,"area":"agents"},{"id":"2604.01193","title":"Embarrassingly Simple Self-Distillation Improves Code Generation","created":"2026-04-01","cited_by_count":40,"area":"distill"},{"id":"2507.02841","title":"StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason","created":"2025-07-03","cited_by_count":39,"area":"lr"},{"id":"2507.15778","title":"Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR","created":"2025-07-21","cited_by_count":39,"area":"lr"},{"id":"2509.07430","title":"The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward","created":"2025-09-09","cited_by_count":37,"area":null},{"id":"2508.11356","title":"ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism","created":"2025-08-15","cited_by_count":36,"area":null},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2512.02472","title":"Guided Self-Evolving LLMs with Minimal Human Supervision","created":"2025-12-02","cited_by_count":35,"area":null},{"id":"2507.05255","title":"Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning","created":"2025-07-07","cited_by_count":34,"area":"lr"},{"id":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34,"area":"lr"},{"id":"2510.10649","title":"Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning","created":"2025-10-12","cited_by_count":34,"area":"lr"},{"id":"2510.11701","title":"Demystifying Reinforcement Learning in Agentic Reasoning","created":"2025-10-13","cited_by_count":33,"area":"lr"},{"id":"2508.05988","title":"Pruning the Unsurprising: Efficient LLM Reasoning via First-Token Surprisal","created":"2025-08-08","cited_by_count":32,"area":"lr"},{"id":"2510.20817","title":"KL-Regularized Reinforcement Learning is Designed to Mode Collapse","created":"2025-10-23","cited_by_count":31,"area":"deeprl"},{"id":"2509.26209","title":"Diversity-Incentivized Exploration for Versatile Reasoning","created":"2025-09-30","cited_by_count":28,"area":"lr"},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2602.13035","title":"Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL","created":"2026-02-13","cited_by_count":27,"area":null},{"id":"2506.17871","title":"LLM Probability Concentration: How Alignment Shrinks the Generative Horizon","created":"2025-06-22","cited_by_count":26,"area":"alignment"},{"id":"2509.25133","title":"Rethinking Entropy Regularization in Large Reasoning Models","created":"2025-09-29","cited_by_count":26,"area":"lr"},{"id":"2509.25666","title":"Nudging the Boundaries of LLM Reasoning","created":"2025-09-30","cited_by_count":26,"area":"lr"},{"id":"2507.03112","title":"RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents","created":"2025-07-03","cited_by_count":25,"area":"lr"},{"id":"2510.03222","title":"Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward","created":"2025-10-03","cited_by_count":25,"area":"lr"},{"id":"2510.13554","title":"Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization","created":"2025-10-15","cited_by_count":25,"area":"lr"},{"id":"2509.26522","title":"Entropy After </Think> for reasoning model early exiting","created":"2025-09-30","cited_by_count":24,"area":"lr"},{"id":"2509.20712","title":"CE-GPPO: Coordinating Entropy via Gradient-Preserving Clipping Policy Optimization in Reinforcement Learning","created":"2025-09-25","cited_by_count":23,"area":"lr"},{"id":"2508.06924","title":"AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning","created":"2025-08-09","cited_by_count":22,"area":"lr"},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2511.05993","title":"Revisiting Entropy in Reinforcement Learning for Large Reasoning Models","created":"2025-11-08","cited_by_count":21,"area":"lr"},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2603.22446","title":"Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs","created":"2026-03-23","cited_by_count":20,"area":"lr"},{"id":"2507.18391","title":"Revisiting LLM Reasoning via Information Bottleneck","created":"2025-07-24","cited_by_count":19,"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":"2601.07408","title":"Outcome-Grounded Advantage Reshaping for Fine-Grained Credit Assignment in Mathematical Reasoning","created":"2026-01-12","cited_by_count":19,"area":"lr"},{"id":"2508.04349","title":"GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy","created":"2025-08-06","cited_by_count":18,"area":"lr"},{"id":"2508.11016","title":"CURE: Critical-Token-Guided Re-Concatenation for Entropy-Collapse Prevention","created":"2025-08-14","cited_by_count":18,"area":"lr"},{"id":"2508.14496","title":"Semantic Energy: Detecting LLM Hallucination Beyond Entropy","created":"2025-08-20","cited_by_count":18,"area":null},{"id":"2510.14807","title":"Beyond the Sampled Token: Preserving Candidate Support in RLVR","created":"2025-10-16","cited_by_count":18,"area":null},{"id":"2508.07534","title":"From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR","created":"2025-08-11","cited_by_count":17,"area":"lr"},{"id":"2509.22576","title":"EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning","created":"2025-09-26","cited_by_count":17,"area":"agents"},{"id":"2509.23285","title":"Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning","created":"2025-09-27","cited_by_count":17,"area":"lr"},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2603.13026","title":"PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses","created":"2026-03-13","cited_by_count":16,"area":"safety"},{"id":"2605.10781","title":"Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR","created":"2026-05-11","cited_by_count":15,"area":"lr"},{"id":"2506.22200","title":"EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework","created":"2025-06-27","cited_by_count":14,"area":"lr"},{"id":"2509.24261","title":"Risk-Sensitive RL for Alleviating Exploration Dilemmas in Large Language Models","created":"2025-09-29","cited_by_count":14,"area":"lr"},{"id":"2602.03412","title":"Verified Critical Step Optimization for LLM Agents","created":"2026-02-03","cited_by_count":14,"area":"agents"},{"id":"2602.19208","title":"How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization","created":"2026-02-22","cited_by_count":14,"area":"lr"},{"id":"2509.25004","title":"CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning","created":"2025-09-29","cited_by_count":13,"area":"lr"},{"id":"2605.19447","title":"What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents","created":"2026-05-19","cited_by_count":13,"area":"agents"},{"id":"2509.00125","title":"Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning","created":"2025-08-29","cited_by_count":12,"area":"lr"},{"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":"2509.26114","title":"Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models","created":"2025-09-30","cited_by_count":12,"area":"lr"},{"id":"2510.00911","title":"RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training","created":"2025-10-01","cited_by_count":12,"area":"lr"},{"id":"2510.08141","title":"SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training","created":"2025-10-09","cited_by_count":12,"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":"2601.08763","title":"Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs","created":"2026-01-13","cited_by_count":12,"area":"lr"},{"id":"2603.13366","title":"Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding","created":"2026-03-09","cited_by_count":12,"area":"lr"},{"id":"2507.19766","title":"UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities","created":"2025-07-26","cited_by_count":11,"area":"lr"},{"id":"2508.09883","title":"Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning","created":"2025-08-13","cited_by_count":11,"area":"lr"},{"id":"2509.16591","title":"Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature","created":"2025-09-20","cited_by_count":11,"area":null},{"id":"2509.22611","title":"Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning","created":"2025-09-26","cited_by_count":11,"area":"lr"},{"id":"2510.10959","title":"Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning","created":"2025-10-13","cited_by_count":11,"area":"lr"},{"id":"2510.23049","title":"Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients","created":"2025-10-27","cited_by_count":11,"area":"lr"},{"id":"2602.01062","title":"SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2602.06717","title":"F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare","created":"2026-02-06","cited_by_count":11,"area":"lr"},{"id":"2602.17550","title":"MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2605.09253","title":"Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation","created":"2026-05-10","cited_by_count":11,"area":"distill"},{"id":"2509.24981","title":"Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards","created":"2025-09-29","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":"2510.11653","title":"MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2512.00908","title":"Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs","created":"2025-11-30","cited_by_count":10,"area":"lr"},{"id":"2601.03190","title":"Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning","created":"2026-01-06","cited_by_count":10,"area":"safety"},{"id":"2605.22263","title":"Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning","created":"2026-05-21","cited_by_count":10,"area":"lr"},{"id":"2606.05152","title":"Reinforcement Learning from Rich Feedback with Distributional DAgger","created":"2026-06-03","cited_by_count":10,"area":"lr"},{"id":"2507.20187","title":"Diversity-Enhanced Reasoning for Subjective Questions","created":"2025-07-27","cited_by_count":9,"area":"lr"},{"id":"2510.08325","title":"Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries","created":"2025-10-09","cited_by_count":9,"area":"lr"},{"id":"2510.16614","title":"Count Counts: Motivating Exploration in LLM Reasoning with Count-based Intrinsic Rewards","created":"2025-10-18","cited_by_count":9,"area":"lr"},{"id":"2601.03823","title":"Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning","created":"2026-01-07","cited_by_count":9,"area":"lr"}],"next_cursor":"100"}