{"total":173,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2512.07783","title":"On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models","created":"2025-12-08","cited_by_count":69,"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":"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":"2510.02245","title":"ExGRPO: Learning to Reason from Experience","created":"2025-10-02","cited_by_count":53,"area":"lr"},{"id":"2510.00915","title":"Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers","created":"2025-10-01","cited_by_count":45,"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":"2510.27606","title":"Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning","created":"2025-10-31","cited_by_count":41,"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":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34,"area":"lr"},{"id":"2510.04040","title":"FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning","created":"2025-10-05","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":"2603.05706","title":"Reasoning Models Struggle to Control their Chains of Thought","created":"2026-03-05","cited_by_count":25,"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":"2603.09206","title":"MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data","created":"2026-03-10","cited_by_count":21,"area":"lr"},{"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":"2507.17842","title":"Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning","created":"2025-07-23","cited_by_count":19,"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":"2603.02146","title":"LongRLVR: Long-Context Reinforcement Learning Requires Verifiable Context Rewards","created":"2026-03-02","cited_by_count":15,"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":"2512.15146","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":"2601.17223","title":"Beyond Outcome Verification: Verifiable Process Reward Models for Structured Reasoning","created":"2026-01-23","cited_by_count":13,"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":"2601.19280","title":"Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning","created":"2026-01-27","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":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2508.13023","title":"G$^2$RPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance","created":"2025-08-18","cited_by_count":10,"area":"lr"},{"id":"2601.10679","title":"Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models","created":"2026-01-15","cited_by_count":10,"area":"lr"},{"id":"2602.12579","title":"VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction","created":"2026-02-13","cited_by_count":10,"area":"lr"},{"id":"2605.09548","title":"Crosslingual On-Policy Self-Distillation for Multilingual Reasoning","created":"2026-05-10","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":"2510.08325","title":"Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries","created":"2025-10-09","cited_by_count":9,"area":"lr"},{"id":"2510.14943","title":"LaSeR: Reinforcement Learning with Last-Token Self-Rewarding","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2602.02301","title":"Advancing General-Purpose Reasoning Models with Modular Gradient Surgery","created":"2026-02-02","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":"2511.13612","title":"P1: Mastering Physics Olympiads with Reinforcement Learning","created":"2025-11-17","cited_by_count":8,"area":"lr"},{"id":"2601.23163","title":"Probing the Trajectories of Reasoning Traces in Large Language Models","created":"2026-01-30","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":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2602.09443","title":"P1-VL: Bridging Visual Perception and Scientific Reasoning in Physics Olympiads","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2604.22074","title":"Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning","created":"2026-04-23","cited_by_count":7,"area":"lr"},{"id":"2605.26958","title":"Tournament-GRPO: Group-Wise Tournament Rewards for Reinforcement Learning in Open-Ended Long-Form Generation","created":"2026-05-26","cited_by_count":7,"area":"lr"},{"id":"2606.23104","title":"ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation","created":"2026-06-22","cited_by_count":7,"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"},{"id":"2602.09598","title":"Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning","created":"2026-02-10","cited_by_count":6,"area":"lr"},{"id":"2602.21420","title":"Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning","created":"2026-02-24","cited_by_count":6,"area":"lr"},{"id":"2603.02091","title":"Learning from Synthetic Data Improves Multi-hop Reasoning","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2603.15255","title":"SAGE: Multi-Agent Self-Evolution for LLM Reasoning","created":"2026-03-16","cited_by_count":6,"area":"lr"},{"id":"2604.08476","title":"Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization","created":"2026-04-09","cited_by_count":6,"area":"lr"},{"id":"2606.18967","title":"EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts","created":"2026-06-17","cited_by_count":6,"area":"lr"},{"id":"2509.21459","title":"A State-of-the-Art SQL Reasoning Model using RLVR","created":"2025-09-25","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":"2603.09249","title":"Social-R1: Towards Human-like Social Reasoning in LLMs","created":"2026-03-10","cited_by_count":5,"area":"lr"},{"id":"2605.07114","title":"Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2606.18089","title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","created":"2026-06-16","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2511.07368","title":"Distributional Biases in Post-Training: A Markovian Analysis of Reasoning Trajectories","created":"2025-11-10","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":"2601.01562","title":"Logics-STEM: Empowering LLM Reasoning via Failure-Driven Post-Training and Document Knowledge Enhancement","created":"2026-01-04","cited_by_count":4,"area":"lr"},{"id":"2601.04537","title":"Linear Dynamics in the RLVR Training of Large Language Models","created":"2026-01-08","cited_by_count":4,"area":"lr"},{"id":"2602.02477","title":"Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time Scalability","created":"2026-02-02","cited_by_count":4,"area":"lr"},{"id":"2602.09782","title":"Flexible Entropy Control in RLVR with a Gradient-Preserving Perspective","created":"2026-02-10","cited_by_count":4,"area":"lr"},{"id":"2602.12395","title":"What does RL improve for Visual Reasoning? A Frankenstein-Style Analysis","created":"2026-02-12","cited_by_count":4,"area":"lr"},{"id":"2602.14225","title":"Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding","created":"2026-02-15","cited_by_count":4,"area":"lr"},{"id":"2603.10725","title":"Towards Robust Speech Deepfake Detection via Human-Inspired Reasoning","created":"2026-03-11","cited_by_count":4,"area":"lr"},{"id":"2605.07153","title":"Beyond Reasoning: Reinforcement Learning Unlocks Parametric Knowledge in LLMs","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"id":"2605.31228","title":"EchoRL: Reinforcement Learning via Rollout Echoing","created":"2026-05-29","cited_by_count":4,"area":"lr"},{"id":"2606.18844","title":"Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation","created":"2026-06-17","cited_by_count":4,"area":"lr"},{"id":"2606.19120","title":"Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation","created":"2026-06-17","cited_by_count":4,"area":"lr"},{"id":"2509.21482","title":"Learning to Reason with Mixture of Tokens","created":"2025-09-25","cited_by_count":3,"area":"lr"},{"id":"2510.17498","title":"Deep Self-Evolving Reasoning","created":"2025-10-20","cited_by_count":3,"area":"lr"},{"id":"2601.09981","title":"DR$^2$Seg: Decomposed Two-Stage Rollouts for Efficient Reasoning Segmentation in Multimodal Large Language Models","created":"2026-01-15","cited_by_count":3,"area":"lr"},{"id":"2602.02545","title":"Beyond Alignment: Expanding Reasoning Capacity via Manifold-Reshaping Policy Optimization","created":"2026-01-30","cited_by_count":3,"area":"lr"},{"id":"2603.20046","title":"Experience is the Best Teacher: Motivating Effective Exploration in Reinforcement Learning for LLMs","created":"2026-03-20","cited_by_count":3,"area":"lr"},{"id":"2604.03004","title":"R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning","created":"2026-04-03","cited_by_count":3,"area":"lr"},{"id":"2604.06192","title":"The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"id":"2605.07654","title":"Reliable Chain-of-Thought via Prefix Consistency","created":"2026-05-08","cited_by_count":3,"area":"lr"},{"id":"2605.08873","title":"CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2605.25603","title":"Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy","created":"2026-05-25","cited_by_count":3,"area":"lr"},{"id":"2606.02578","title":"Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2606.15532","title":"EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management","created":"2026-06-14","cited_by_count":3,"area":"lr"},{"id":"2606.18954","title":"GraphPO: Graph-based Policy Optimization for Reasoning Models","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2606.23557","title":"Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views","created":"2026-06-22","cited_by_count":3,"area":"lr"},{"id":"2508.08149","title":"REX-RAG: Reasoning Exploration with Policy Correction in Retrieval-Augmented Generation","created":"2025-08-11","cited_by_count":2,"area":"lr"},{"id":"2509.21124","title":"Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns","created":"2025-09-25","cited_by_count":2,"area":"lr"},{"id":"2510.24126","title":"Reinforcement Learning for Long-Horizon Multi-Turn Search Agents","created":"2025-10-28","cited_by_count":2,"area":"lr"},{"id":"2601.11374","title":"Reward Modeling for Scientific Writing Evaluation","created":"2026-01-16","cited_by_count":2,"area":"lr"},{"id":"2602.08281","title":"New Skills or Sharper Primitives? A Probabilistic Perspective on the Emergence of Reasoning in RLVR","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2602.11675","title":"Epistemic Regret Minimization: Label-Free Causal Critique Beyond Outcome Reward","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2603.27375","title":"Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models","created":"2026-03-28","cited_by_count":2,"area":"lr"},{"id":"2604.00442","title":"Execution-Verified Reinforcement Learning for Optimization Modeling","created":"2026-04-01","cited_by_count":2,"area":"lr"},{"id":"2604.17912","title":"Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-Thought","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2604.18574","title":"When Can LLMs Learn to Reason with Weak Supervision?","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2604.20705","title":"SSL-R1: Self-Supervised Visual Reinforcement Post-Training for Multimodal Large Language Models","created":"2026-04-22","cited_by_count":2,"area":"lr"},{"id":"2605.16874","title":"Reasoning Can Be Restored by Correcting a Few Decision Tokens","created":"2026-05-16","cited_by_count":2,"area":"lr"},{"id":"2606.06058","title":"MDP-GRPO: Stabilized Group Relative Policy Optimization for Multi-Constraint Instruction Following","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2606.06080","title":"On Advantage Estimates for Max@K Policy Gradients","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2606.22938","title":"Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently","created":"2026-06-22","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}