{"total":195,"rows":[{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559,"area":"lr"},{"id":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344,"area":"lr"},{"id":"2506.14245","title":"Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs","created":"2025-06-17","cited_by_count":289,"area":"lr"},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209,"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":"2506.21734","title":"Hierarchical Reasoning Model","created":"2025-06-26","cited_by_count":177,"area":"lr"},{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172,"area":"lr"},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"area":"lr"},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2506.02177","title":"Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts","created":"2025-06-02","cited_by_count":113,"area":"lr"},{"id":"2506.20512","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","created":"2025-06-25","cited_by_count":113,"area":"lr"},{"id":"2506.19767","title":"SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning","created":"2025-06-24","cited_by_count":84,"area":"lr"},{"id":"2507.10532","title":"Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination","created":"2025-07-14","cited_by_count":82,"area":"lr"},{"id":"2505.21444","title":"Can Large Reasoning Models Self-Train?","created":"2025-05-27","cited_by_count":68,"area":"lr"},{"id":"2506.09026","title":"e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"id":"2505.19914","title":"Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles","created":"2025-05-26","cited_by_count":56,"area":"lr"},{"id":"2506.17238","title":"Training a Scientific Reasoning Model for Chemistry","created":"2025-06-04","cited_by_count":56,"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":"2505.20347","title":"SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data","created":"2025-05-25","cited_by_count":51,"area":"lr"},{"id":"2505.15117","title":"An Empirical Study on Reinforcement Learning for Reasoning-Search Interleaved LLM Agents","created":"2025-05-21","cited_by_count":46,"area":"lr"},{"id":"2507.13266","title":"QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation","created":"2025-07-17","cited_by_count":44,"area":"lr"},{"id":"2601.18779","title":"POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration","created":"2026-01-26","cited_by_count":42,"area":"lr"},{"id":"2510.27606","title":"Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning","created":"2025-10-31","cited_by_count":41,"area":"lr"},{"id":"2505.18116","title":"NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning","created":"2025-05-23","cited_by_count":38,"area":"lr"},{"id":"2507.12856","title":"Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)","created":"2025-07-17","cited_by_count":38,"area":"lr"},{"id":"2508.00222","title":"RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization","created":"2025-07-31","cited_by_count":35,"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":"2507.06485","title":"Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning","created":"2025-07-09","cited_by_count":33,"area":"lr"},{"id":"2506.04245","title":"Contextual Integrity in LLMs via Reasoning and Reinforcement Learning","created":"2025-05-29","cited_by_count":31,"area":"lr"},{"id":"2509.25300","title":"Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning","created":"2025-09-29","cited_by_count":29,"area":"lr"},{"id":"2510.19363","title":"LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts","created":"2025-10-22","cited_by_count":29,"area":"lr"},{"id":"2505.15692","title":"TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning","created":"2025-05-21","cited_by_count":28,"area":"lr"},{"id":"2510.07364","title":"Base Models Know How to Reason, Thinking Models Learn When","created":"2025-10-08","cited_by_count":27,"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":"2505.18675","title":"ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Maps","created":"2025-05-24","cited_by_count":23,"area":"lr"},{"id":"2505.24098","title":"HardTests: Synthesizing High-Quality Test Cases for LLM Coding","created":"2025-05-30","cited_by_count":23,"area":"lr"},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23,"area":"lr"},{"id":"2601.22311","title":"Why Reasoning Fails to Plan: A Planning-Centric Analysis of Long-Horizon Decision Making in LLM Agents","created":"2026-01-29","cited_by_count":23,"area":"lr"},{"id":"2506.00070","title":"Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics","created":"2025-05-29","cited_by_count":21,"area":"lr"},{"id":"2507.04136","title":"A Technical Survey of Reinforcement Learning Techniques for Large Language Models","created":"2025-07-05","cited_by_count":21,"area":"lr"},{"id":"2508.02260","title":"Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning","created":"2025-08-04","cited_by_count":21,"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":"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":"2510.13888","title":"Reliable Fine-Grained Evaluation of Natural Language Math Proofs","created":"2025-10-14","cited_by_count":18,"area":"lr"},{"id":"2505.18706","title":"Steering LLM Reasoning Through Bias-Only Adaptation","created":"2025-05-24","cited_by_count":16,"area":"lr"},{"id":"2505.20087","title":"Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models","created":"2025-05-26","cited_by_count":16,"area":"lr"},{"id":"2507.06181","title":"CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization","created":"2025-07-08","cited_by_count":16,"area":"lr"},{"id":"2510.04454","title":"Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","cited_by_count":16,"area":"lr"},{"id":"2505.17063","title":"Synthetic Data RL: Task Definition Is All You Need","created":"2025-05-18","cited_by_count":15,"area":"lr"},{"id":"2510.02172","title":"RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization","created":"2025-10-02","cited_by_count":15,"area":"lr"},{"id":"2505.14216","title":"Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoning","created":"2025-05-20","cited_by_count":14,"area":"lr"},{"id":"2505.24105","title":"Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning","created":"2025-05-30","cited_by_count":14,"area":"lr"},{"id":"2508.09670","title":"MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement","created":"2025-08-13","cited_by_count":14,"area":"lr"},{"id":"2509.03059","title":"Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers","created":"2025-09-03","cited_by_count":14,"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":"2602.04118","title":"Learning to Reason in 13 Parameters","created":"2026-02-04","cited_by_count":14,"area":"lr"},{"id":"2507.02834","title":"ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning","created":"2025-07-03","cited_by_count":13,"area":"lr"},{"id":"2512.15146","title":"Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning","created":"2025-12-17","cited_by_count":13,"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":"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":"2510.26491","title":"Data-Efficient RLVR via Off-Policy Influence Guidance","created":"2025-10-30","cited_by_count":12,"area":"lr"},{"id":"2512.13095","title":"ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2603.19880","title":"What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time","created":"2026-03-20","cited_by_count":12,"area":"lr"},{"id":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"area":"lr"},{"id":"2509.25454","title":"DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2602.17053","title":"RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models","created":"2026-02-19","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":"2603.11682","title":"Entropy-Preserving Reinforcement Learning","created":"2026-03-12","cited_by_count":11,"area":"lr"},{"id":"2505.22756","title":"Decomposing Elements of Problem Solving: What \"Math\" Does RL Teach?","created":"2025-05-28","cited_by_count":10,"area":"lr"},{"id":"2507.06573","title":"From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization","created":"2025-07-09","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":"2606.15455","title":"Understanding Diversity Collapse in RLVR via the Lens of Overtraining","created":"2026-06-13","cited_by_count":10,"area":"lr"},{"id":"2506.11480","title":"LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment","created":"2025-06-13","cited_by_count":9,"area":"lr"},{"id":"2507.00726","title":"Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess","created":"2025-07-01","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":"2510.07312","title":"h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning","created":"2025-10-08","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":"2510.10248","title":"Reasoning-Enhanced Large Language Models for Molecular Property Prediction","created":"2025-10-11","cited_by_count":9,"area":"lr"},{"id":"2512.00218","title":"Reasoning Under Pressure: How do Training Incentives Influence Chain-of-Thought Monitorability?","created":"2025-11-28","cited_by_count":9,"area":"lr"},{"id":"2603.02203","title":"Tool Verification for Test-Time Reinforcement Learning","created":"2026-03-02","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":"2505.24872","title":"ProxyThinker: Test-Time Guidance through Small Visual Reasoners","created":"2025-05-30","cited_by_count":8,"area":"lr"},{"id":"2506.07104","title":"How Far Are We from Optimal Reasoning Efficiency?","created":"2025-06-08","cited_by_count":8,"area":"lr"},{"id":"2508.20549","title":"MedGR$^2$: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning","created":"2025-08-28","cited_by_count":8,"area":"lr"},{"id":"2509.06608","title":"Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors","created":"2025-09-08","cited_by_count":8,"area":"lr"},{"id":"2509.25160","title":"GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts","created":"2025-09-29","cited_by_count":8,"area":"lr"},{"id":"2510.26143","title":"Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math","created":"2025-10-30","cited_by_count":8,"area":"lr"},{"id":"2510.27072","title":"Towards Understanding Self-play for LLM Reasoning","created":"2025-10-31","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":"2604.07165","title":"Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization","created":"2026-04-08","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":"2512.04748","title":"Model Whisper: Steering Vectors Unlock Large Language Models' Potential in Test-time","created":"2025-12-04","cited_by_count":7,"area":"lr"},{"id":"2602.17633","title":"When to Trust the Cheap Check: Weak and Strong Verification for Reasoning","created":"2026-02-19","cited_by_count":7,"area":"lr"},{"id":"2506.09967","title":"Resa: Transparent Reasoning Models via SAEs","created":"2025-06-11","cited_by_count":6,"area":"lr"},{"id":"2510.27044","title":"Limits of Generalization in RLVR: Two Case Studies in Mathematical Reasoning","created":"2025-10-30","cited_by_count":6,"area":"lr"}],"next_cursor":"100"}