{"total":852,"rows":[{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982,"area":"lr"},{"id":"2504.07615","title":"VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model","created":"2025-04-10","cited_by_count":526,"area":"lr"},{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497,"area":"lr"},{"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":"2503.24290","title":"Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model","created":"2025-03-31","cited_by_count":461,"area":"lr"},{"id":"2601.18734","title":"Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models","created":"2026-01-26","cited_by_count":455,"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":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2504.08837","title":"VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning","created":"2025-04-10","cited_by_count":323,"area":"lr"},{"id":"2504.20571","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","created":"2025-04-29","cited_by_count":295,"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":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281,"area":"lr"},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"id":"2504.11456","title":"DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning","created":"2025-04-15","cited_by_count":280,"area":"lr"},{"id":"2505.15966","title":"Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning","created":"2025-05-21","cited_by_count":278,"area":"lr"},{"id":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275,"area":"lr"},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263,"area":"lr"},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246,"area":"lr"},{"id":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219,"area":"lr"},{"id":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210,"area":"lr"},{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209,"area":"lr"},{"id":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193,"area":"lr"},{"id":"2504.12216","title":"d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning","created":"2025-04-16","cited_by_count":186,"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":"2509.04259","title":"RL's Razor: Why Online Reinforcement Learning Forgets Less","created":"2025-09-04","cited_by_count":176,"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":"2504.02546","title":"GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning","created":"2025-04-03","cited_by_count":150,"area":"lr"},{"id":"2509.02479","title":"SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning","created":"2025-09-02","cited_by_count":146,"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":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"area":"lr"},{"id":"2504.07912","title":"Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining","created":"2025-04-10","cited_by_count":129,"area":"lr"},{"id":"2505.13379","title":"Thinkless: LLM Learns When to Think","created":"2025-05-19","cited_by_count":113,"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":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111,"area":"lr"},{"id":"2506.24119","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","created":"2025-06-30","cited_by_count":100,"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":"2503.22342","title":"CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models","created":"2025-03-28","cited_by_count":96,"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":"2505.12346","title":"SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization","created":"2025-05-18","cited_by_count":89,"area":"lr"},{"id":"2504.13055","title":"NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation","created":"2025-04-17","cited_by_count":86,"area":"lr"},{"id":"2506.18254","title":"RLPR: Extrapolating RLVR to General Domains without Verifiers","created":"2025-06-23","cited_by_count":85,"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":"2505.23678","title":"Grounded Reinforcement Learning for Visual Reasoning","created":"2025-05-29","cited_by_count":83,"area":"lr"},{"id":"2504.09696","title":"GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models","created":"2025-04-13","cited_by_count":82,"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":"2603.11137","title":"Scaling Reasoning Efficiently via Relaxed On-Policy Distillation","created":"2026-03-11","cited_by_count":82,"area":"lr"},{"id":"2504.05185","title":"Concise Reasoning via Reinforcement Learning","created":"2025-04-07","cited_by_count":79,"area":"lr"},{"id":"2505.11821","title":"Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit Assignment","created":"2025-05-17","cited_by_count":79,"area":"lr"},{"id":"2504.00050","title":"JudgeLRM: Large Reasoning Models as a Judge","created":"2025-03-31","cited_by_count":78,"area":"lr"},{"id":"2505.21493","title":"Reinforcing General Reasoning without Verifiers","created":"2025-05-27","cited_by_count":77,"area":"lr"},{"id":"2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","created":"2026-04-02","cited_by_count":76,"area":"lr"},{"id":"2505.23564","title":"Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models","created":"2025-05-29","cited_by_count":75,"area":"lr"},{"id":"2508.09726","title":"Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning","created":"2025-08-13","cited_by_count":75,"area":"lr"},{"id":"2505.15810","title":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","created":"2025-05-21","cited_by_count":74,"area":"lr"},{"id":"2507.08838","title":"wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models","created":"2025-07-07","cited_by_count":71,"area":"lr"},{"id":"2504.20024","title":"SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning","created":"2025-04-28","cited_by_count":68,"area":"lr"},{"id":"2505.21444","title":"Can Large Reasoning Models Self-Train?","created":"2025-05-27","cited_by_count":68,"area":"lr"},{"id":"2506.08343","title":"Wait, We Don't Need to \"Wait\"! Removing Thinking Tokens Improves Reasoning Efficiency","created":"2025-06-10","cited_by_count":66,"area":"lr"},{"id":"2504.09641","title":"TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning","created":"2025-04-13","cited_by_count":62,"area":"lr"},{"id":"2602.05125","title":"Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks","created":"2026-02-04","cited_by_count":62,"area":"lr"},{"id":"2509.13305","title":"WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning","created":"2025-09-16","cited_by_count":61,"area":"lr"},{"id":"2506.10910","title":"Magistral","created":"2025-06-12","cited_by_count":60,"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":"2506.09026","title":"e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"id":"2509.02208","title":"Baichuan-M2: Scaling Medical Capability with Large Verifier System","created":"2025-09-02","cited_by_count":59,"area":"lr"},{"id":"2506.01713","title":"SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning","created":"2025-06-02","cited_by_count":57,"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":"2506.05316","title":"Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay","created":"2025-06-05","cited_by_count":56,"area":"lr"},{"id":"2508.08221","title":"Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning","created":"2025-08-11","cited_by_count":56,"area":"lr"},{"id":"2511.08567","title":"The Path Not Taken: RLVR Provably Learns Off the Principals","created":"2025-11-11","cited_by_count":56,"area":"lr"},{"id":"2512.03043","title":"OneThinker: All-in-one Reasoning Model for Image and Video","created":"2025-12-02","cited_by_count":56,"area":"lr"},{"id":"2506.21277","title":"HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context","created":"2025-06-26","cited_by_count":55,"area":"lr"},{"id":"2510.08191","title":"Training-Free Group Relative Policy Optimization","created":"2025-10-09","cited_by_count":55,"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":"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":"2510.01161","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":"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":"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":"2504.15275","title":"Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning","created":"2025-04-21","cited_by_count":50,"area":"lr"},{"id":"2505.17667","title":"QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning","created":"2025-05-23","cited_by_count":50,"area":"lr"},{"id":"2505.18822","title":"AdaCtrl: Towards Adaptive and Controllable Reasoning via Difficulty-Aware Budgeting","created":"2025-05-24","cited_by_count":50,"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":"2602.22817","title":"Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-02-26","cited_by_count":49,"area":"lr"},{"id":"2504.12329","title":"Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time","created":"2025-04-12","cited_by_count":48,"area":"lr"},{"id":"2506.16141","title":"GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning","created":"2025-06-19","cited_by_count":47,"area":"lr"},{"id":"2606.11709","title":"RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation","created":"2026-06-10","cited_by_count":45,"area":"lr"},{"id":"2504.21277","title":"Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models","created":"2025-04-30","cited_by_count":44,"area":"lr"},{"id":"2505.12929","title":"Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs","created":"2025-05-19","cited_by_count":44,"area":"lr"},{"id":"2504.04022","title":"Rethinking Reflection in Pre-Training","created":"2025-04-05","cited_by_count":43,"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":"2506.08989","title":"SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":42,"area":"lr"},{"id":"2509.03646","title":"Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning","created":"2025-09-03","cited_by_count":42,"area":"lr"},{"id":"2505.23433","title":"Diversity-Aware Policy Optimization for Large Language Model Reasoning","created":"2025-05-29","cited_by_count":41,"area":"lr"},{"id":"2506.02208","title":"KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning","created":"2025-06-02","cited_by_count":41,"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":"2509.02333","title":"DCPO: Dynamic Clipping Policy Optimization","created":"2025-09-02","cited_by_count":40,"area":"lr"},{"id":"2509.15207","title":"FlowRL: Matching Reward Distributions for LLM Reasoning","created":"2025-09-18","cited_by_count":40,"area":"lr"},{"id":"2506.09340","title":"RePO: Replay-Enhanced Policy Optimization","created":"2025-06-11","cited_by_count":39,"area":"lr"}],"next_cursor":"100"}