{"total":189,"rows":[{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485,"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":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2508.05629","title":"On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification","created":"2025-08-07","cited_by_count":127,"area":"lr"},{"id":"2506.07527","title":"Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions","created":"2025-06-09","cited_by_count":97,"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":"2506.03106","title":"Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback","created":"2025-06-03","cited_by_count":90,"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":"2603.11137","title":"Scaling Reasoning Efficiently via Relaxed On-Policy Distillation","created":"2026-03-11","cited_by_count":82,"area":"lr"},{"id":"2510.05592","title":"In-the-Flow Agentic System Optimization for Effective Planning and Tool Use","created":"2025-10-07","cited_by_count":72,"area":"lr"},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2506.04207","title":"Advancing Multimodal Reasoning: From Optimized Cold Start to Staged Reinforcement Learning","created":"2025-06-04","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":"2510.19807","title":"Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning","created":"2025-10-22","cited_by_count":52,"area":"lr"},{"id":"2508.13755","title":"Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration","created":"2025-08-19","cited_by_count":43,"area":"lr"},{"id":"2509.24304","title":"FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting","created":"2025-09-29","cited_by_count":42,"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":"2506.09340","title":"RePO: Replay-Enhanced Policy Optimization","created":"2025-06-11","cited_by_count":39,"area":"lr"},{"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":"2507.07451","title":"RLEP: Reinforcement Learning with Experience Replay for LLM Reasoning","created":"2025-07-10","cited_by_count":39,"area":"lr"},{"id":"2510.09285","title":"Spotlight on Token Perception for Multimodal Reinforcement Learning","created":"2025-10-10","cited_by_count":39,"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":"2509.19803","title":"VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models","created":"2025-09-24","cited_by_count":36,"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":"2605.06387","title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","created":"2026-05-07","cited_by_count":35,"area":"lr"},{"id":"2505.23585","title":"On-Policy RL with Optimal Reward Baseline","created":"2025-05-29","cited_by_count":34,"area":"lr"},{"id":"2604.13010","title":"Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation","created":"2026-04-14","cited_by_count":33,"area":"lr"},{"id":"2509.18851","title":"NGRPO: Negative-enhanced Group Relative Policy Optimization","created":"2025-09-23","cited_by_count":32,"area":"lr"},{"id":"2509.06948","title":"Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning","created":"2025-09-08","cited_by_count":30,"area":"lr"},{"id":"2509.18521","title":"APRIL: Active Partial Rollouts in Reinforcement Learning to Tame Long-tail Generation","created":"2025-09-23","cited_by_count":30,"area":"lr"},{"id":"2505.14810","title":"Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models","created":"2025-05-20","cited_by_count":28,"area":"lr"},{"id":"2509.26209","title":"Diversity-Incentivized Exploration for Versatile Reasoning","created":"2025-09-30","cited_by_count":28,"area":"lr"},{"id":"2508.02298","title":"CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment","created":"2025-08-04","cited_by_count":26,"area":"lr"},{"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":"2511.12344","title":"Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning","created":"2025-11-15","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":"2508.08636","title":"InternBootcamp: Boosting LLM Reasoning with Verifiable Task Scaling","created":"2025-08-12","cited_by_count":20,"area":"lr"},{"id":"2602.03143","title":"Self-Hinting Language Models Enhance Reinforcement Learning","created":"2026-02-03","cited_by_count":20,"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":"2508.11016","title":"CURE: Critical-Token-Guided Re-Concatenation for Entropy-Collapse Prevention","created":"2025-08-14","cited_by_count":18,"area":"lr"},{"id":"2508.17784","title":"Proximal Supervised Fine-Tuning","created":"2025-08-25","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":"2507.10616","title":"Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them","created":"2025-07-13","cited_by_count":15,"area":"lr"},{"id":"2509.24203","title":"Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends","created":"2025-09-29","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":"2506.23840","title":"Do Thinking Tokens Help or Trap? Towards More Efficient Large Reasoning Model","created":"2025-06-30","cited_by_count":14,"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":"2510.09388","title":"Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts","created":"2025-10-10","cited_by_count":14,"area":"lr"},{"id":"2601.14209","title":"InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning","created":"2026-01-20","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":"2604.06628","title":"Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability","created":"2026-04-08","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":"2510.04028","title":"The Debate on RLVR Reasoning Capability Boundary: Shrinkage, Expansion, or Both? A Two-Stage Dynamic View","created":"2025-10-05","cited_by_count":13,"area":"lr"},{"id":"2512.21540","title":"Leash: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model","created":"2025-12-25","cited_by_count":13,"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":"2604.00698","title":"Learning to Hint for Reinforcement Learning","created":"2026-04-01","cited_by_count":12,"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":"2609.04108","title":"Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR","created":"2026-09-03","cited_by_count":11,"area":"lr"},{"id":"2507.20187","title":"Diversity-Enhanced Reasoning for Subjective Questions","created":"2025-07-27","cited_by_count":9,"area":"lr"},{"id":"2508.07616","title":"ThinkTuning: Instilling Cognitive Reflections without Distillation","created":"2025-08-11","cited_by_count":9,"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":"2512.06337","title":"DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization","created":"2025-12-06","cited_by_count":9,"area":"lr"},{"id":"2602.02244","title":"Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2604.23747","title":"SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning","created":"2026-04-26","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":"2509.23657","title":"Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2511.09907","title":"Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis","created":"2025-11-13","cited_by_count":8,"area":"lr"},{"id":"2602.20722","title":"Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning","created":"2026-02-24","cited_by_count":8,"area":"lr"},{"id":"2505.21908","title":"Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding","created":"2025-05-28","cited_by_count":7,"area":"lr"},{"id":"2508.07809","title":"EvoCoT: Overcoming the Exploration Bottleneck in Reinforcement Learning","created":"2025-08-11","cited_by_count":7,"area":"lr"},{"id":"2508.08641","title":"MiGrATe: Mixed-Policy GRPO for Adaptation at Test-Time","created":"2025-08-12","cited_by_count":7,"area":"lr"},{"id":"2510.04140","title":"Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs","created":"2025-10-05","cited_by_count":7,"area":"lr"},{"id":"2512.13106","title":"TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning","created":"2025-12-15","cited_by_count":7,"area":"lr"},{"id":"2602.14147","title":"LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models","created":"2026-02-15","cited_by_count":7,"area":"lr"},{"id":"2603.03292","title":"From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG","created":"2026-02-06","cited_by_count":7,"area":"lr"},{"id":"2607.19313","title":"Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information","created":"2026-07-21","cited_by_count":7,"area":"lr"},{"id":"2509.04059","title":"Towards an AI Musician: Synthesizing Sheet Music Problems for Musical Reasoning","created":"2025-09-04","cited_by_count":6,"area":"lr"},{"id":"2601.07389","title":"On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training","created":"2026-01-12","cited_by_count":6,"area":"lr"},{"id":"2605.19461","title":"Beyond Mode Collapse: Distribution Matching for Diverse Reasoning","created":"2026-05-19","cited_by_count":6,"area":"lr"},{"id":"2608.03972","title":"ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning","created":"2026-08-04","cited_by_count":6,"area":"lr"},{"id":"2506.04913","title":"Dissecting Long-Chain-of-Thought Reasoning Models: An Empirical Study","created":"2025-06-05","cited_by_count":5,"area":"lr"},{"id":"2506.23061","title":"Empowering Small VLMs to Think with Dynamic Memorization and Exploration","created":"2025-06-29","cited_by_count":5,"area":"lr"},{"id":"2510.06410","title":"Off-Trajectory Reasoning: Can LLMs Collaborate on Reasoning Trajectory?","created":"2025-10-07","cited_by_count":5,"area":"lr"},{"id":"2510.09001","title":"DARO: Difficulty-Aware Reweighting Policy Optimization","created":"2025-10-10","cited_by_count":5,"area":"lr"},{"id":"2602.08498","title":"Characterizing, Evaluating, and Optimizing Complex Reasoning","created":"2026-02-09","cited_by_count":5,"area":"lr"},{"id":"2603.04597","title":"Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning","created":"2026-03-04","cited_by_count":5,"area":"lr"},{"id":"2605.05965","title":"Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVR","created":"2026-05-07","cited_by_count":5,"area":"lr"},{"id":"2606.08708","title":"PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping","created":"2026-06-07","cited_by_count":5,"area":"lr"},{"id":"2606.22317","title":"Curriculum Reinforcement Learning Can Incentivize Reasoning Capacity in LLMs Beyond the Base Model","created":"2026-06-21","cited_by_count":5,"area":"lr"},{"id":"2607.28449","title":"Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models","created":"2026-07-30","cited_by_count":5,"area":"lr"},{"id":"2508.06412","title":"Sample-efficient LLM Optimization with Reset Replay","created":"2025-08-08","cited_by_count":4,"area":"lr"},{"id":"2509.02522","title":"Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR","created":"2025-09-02","cited_by_count":4,"area":"lr"},{"id":"2509.16990","title":"Advancing Speech Understanding in Speech-Aware Language Models with GRPO","created":"2025-09-21","cited_by_count":4,"area":"lr"},{"id":"2510.08540","title":"MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization","created":"2025-10-09","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":"2601.22900","title":"MulFeRL: Enhancing Reinforcement Learning with Verbal Feedback in a Multi-turn Loop","created":"2026-01-30","cited_by_count":4,"area":"lr"},{"id":"2604.04767","title":"Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2605.15224","title":"ICRL: Learning to Internalize Self-Critique with Reinforcement Learning","created":"2026-05-13","cited_by_count":4,"area":"lr"}],"next_cursor":"100"}