{"total":63,"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":"2505.00127","title":"Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs","created":"2025-04-30","cited_by_count":117,"area":"lr"},{"id":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111,"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":"2505.10832","title":"Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL","created":"2025-05-16","cited_by_count":62,"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":"2510.02245","title":"ExGRPO: Learning to Reason from Experience","created":"2025-10-02","cited_by_count":53,"area":"lr"},{"id":"2505.11277","title":"Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning","created":"2025-05-16","cited_by_count":35,"area":"lr"},{"id":"2508.10293","title":"Promoting Efficient Reasoning with Verifiable Stepwise Reward","created":"2025-08-14","cited_by_count":28,"area":"lr"},{"id":"2510.00194","title":"GRPO-$\\lambda$: Credit Assignment improves LLM Reasoning","created":"2025-09-30","cited_by_count":23,"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":"2601.20614","title":"Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation","created":"2026-01-28","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":"2505.19094","title":"SATORI-R1: Incentivizing Multimodal Reasoning through Explicit Visual Anchoring","created":"2025-05-25","cited_by_count":17,"area":"lr"},{"id":"2505.12366","title":"DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization","created":"2025-05-18","cited_by_count":16,"area":"lr"},{"id":"2601.21919","title":"Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning","created":"2026-01-29","cited_by_count":13,"area":"lr"},{"id":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2510.25992","title":"Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning","created":"2025-10-29","cited_by_count":11,"area":"lr"},{"id":"2603.26535","title":"PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization","created":"2026-03-27","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":"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":"2505.13261","title":"Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning","created":"2025-05-19","cited_by_count":7,"area":"lr"},{"id":"2505.13697","title":"RL in Name Only? Analyzing the Structural Assumptions in RL post-training for LLMs","created":"2025-05-19","cited_by_count":7,"area":"lr"},{"id":"2507.04348","title":"SmartThinker: Learning to Compress and Preserve Reasoning by Step-Level Length Control","created":"2025-07-06","cited_by_count":7,"area":"lr"},{"id":"2602.05548","title":"Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty Adaptation","created":"2026-02-05","cited_by_count":7,"area":"lr"},{"id":"2605.21125","title":"Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation","created":"2026-05-20","cited_by_count":7,"area":"lr"},{"id":"2505.19862","title":"REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning","created":"2025-05-26","cited_by_count":6,"area":"lr"},{"id":"2508.05383","title":"StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models","created":"2025-08-07","cited_by_count":6,"area":"lr"},{"id":"2510.27042","title":"e1: Learning Adaptive Control of Reasoning Effort","created":"2025-10-30","cited_by_count":6,"area":"lr"},{"id":"2601.06801","title":"Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2507.22716","title":"From Sufficiency to Reflection: Reinforcement-Guided Thinking Quality in Retrieval-Augmented Reasoning for LLMs","created":"2025-07-30","cited_by_count":5,"area":"lr"},{"id":"2509.07558","title":"VL Norm: Rethink Loss Aggregation in RLVR","created":"2025-09-09","cited_by_count":4,"area":"lr"},{"id":"2510.02249","title":"Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation","created":"2025-10-02","cited_by_count":4,"area":"lr"},{"id":"2510.15374","title":"Towards Flash Thinking via Decoupled Advantage Policy Optimization","created":"2025-10-17","cited_by_count":4,"area":"lr"},{"id":"2512.14944","title":"PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs","created":"2025-12-16","cited_by_count":4,"area":"lr"},{"id":"2507.01327","title":"Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy","created":"2025-07-02","cited_by_count":3,"area":"lr"},{"id":"2510.03259","title":"Verifying Meta-Awareness via Predictive Rewards in Reasoning Models","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2603.01106","title":"DIVA-GRPO: Enhancing Multimodal Reasoning through Difficulty-Adaptive Variant Advantage","created":"2026-03-01","cited_by_count":3,"area":"lr"},{"id":"2505.23247","title":"Accelerating RLHF Training with Reward Variance Increase","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2510.21398","title":"Boosting Accuracy and Efficiency of Budget Forcing in LLMs via Reinforcement Learning for Mathematical Reasoning","created":"2025-10-24","cited_by_count":2,"area":"lr"},{"id":"2604.23333","title":"Process Supervision of Confidence Margin for Calibrated LLM Reasoning","created":"2026-04-25","cited_by_count":2,"area":"lr"},{"id":"2605.11467","title":"Drop the Act: Probe-Filtered RL for Faithful Chain-of-Thought Reasoning","created":"2026-05-12","cited_by_count":2,"area":"lr"},{"id":"2608.20256","title":"Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation","created":"2026-08-20","cited_by_count":2,"area":"lr"},{"id":"2601.06795","title":"GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization with Enhanced Training Data Utilization for Sample-Constrained Reinforcement Learning","created":"2026-01-11","cited_by_count":1,"area":"lr"},{"id":"2601.08403","title":"Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs","created":"2026-01-13","cited_by_count":1,"area":"lr"},{"id":"2601.22478","title":"Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2601.22521","title":"One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.10019","title":"ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning","created":"2026-02-10","cited_by_count":1,"area":"lr"},{"id":"2605.19358","title":"Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2605.27293","title":"BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2605.30789","title":"Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.03094","title":"FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2606.08974","title":"Diverse Thinking Schemata Elicit Better Reasoning in Large Language Models","created":"2026-06-08","cited_by_count":1,"area":"lr"},{"id":"2509.25941","title":"Boosting Process-Correct CoT Reasoning by Modeling Solvability of Multiple-Choice QA","created":"2025-09-30","cited_by_count":0,"area":"lr"},{"id":"2510.01165","title":"GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoning","created":"2025-10-01","cited_by_count":0,"area":"lr"},{"id":"2510.25065","title":"Rewarding Structural Conformance of Reasoning using Process Mining","created":"2025-10-29","cited_by_count":0,"area":"lr"},{"id":"2511.06722","title":"Revisiting the Data Sampling in Multimodal Post-training from a Difficulty-Distinguish View","created":"2025-11-10","cited_by_count":0,"area":"lr"},{"id":"2602.07559","title":"VERIFY-RL: Verifiable Recursive Decomposition for Reinforcement Learning in Mathematical Reasoning","created":"2026-02-07","cited_by_count":0,"area":"lr"},{"id":"2603.18533","title":"Balancing the Reasoning Load: Difficulty-Differentiated Policy Optimization with Length Redistribution for Efficient and Robust Reinforcement Learning","created":"2026-03-19","cited_by_count":0,"area":"lr"},{"id":"2604.02007","title":"Apriel-Reasoner: RL Post-Training for General-Purpose and Efficient Reasoning","created":"2026-04-02","cited_by_count":0,"area":"lr"},{"id":"2606.11209","title":"ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward","created":"2026-04-23","cited_by_count":0,"area":"lr"},{"id":"2610.06993","title":"DART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution Strategies","created":"2026-10-04","cited_by_count":0,"area":"lr"}],"next_cursor":null}