{"total":98,"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":"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":"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":"2504.13818","title":"Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning","created":"2025-04-18","cited_by_count":84,"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":"2507.08838","title":"wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models","created":"2025-07-07","cited_by_count":71,"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":"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":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"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":"2505.12929","title":"Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs","created":"2025-05-19","cited_by_count":44,"area":"lr"},{"id":"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":"2505.13988","title":"The Hallucination Tax of Reinforcement Finetuning","created":"2025-05-20","cited_by_count":40,"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":"2505.05315","title":"Scalable Chain of Thoughts via Elastic Reasoning","created":"2025-05-08","cited_by_count":34,"area":"lr"},{"id":"2509.18851","title":"NGRPO: Negative-enhanced Group Relative Policy Optimization","created":"2025-09-23","cited_by_count":32,"area":"lr"},{"id":"2601.21590","title":"Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening","created":"2026-01-29","cited_by_count":31,"area":"lr"},{"id":"2510.04996","title":"Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL Objectives","created":"2025-10-06","cited_by_count":25,"area":"lr"},{"id":"2505.02391","title":"Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL","created":"2025-05-05","cited_by_count":24,"area":"lr"},{"id":"2505.20686","title":"Accelerating RL for LLM Reasoning with Optimal Advantage Regression","created":"2025-05-27","cited_by_count":24,"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":"2505.15801","title":"VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models","created":"2025-05-21","cited_by_count":20,"area":"lr"},{"id":"2510.07242","title":"Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense","created":"2025-10-08","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":"2505.11595","title":"Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO","created":"2025-05-16","cited_by_count":19,"area":"lr"},{"id":"2505.10554","title":"Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models","created":"2025-05-15","cited_by_count":18,"area":"lr"},{"id":"2510.13651","title":"What is the objective of reasoning with reinforcement learning?","created":"2025-10-15","cited_by_count":18,"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":"2507.02834","title":"ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning","created":"2025-07-03","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":"2507.12399","title":"ROC-n-reroll: How verifier imperfection affects test-time scaling","created":"2025-07-16","cited_by_count":12,"area":"lr"},{"id":"2510.00911","title":"RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training","created":"2025-10-01","cited_by_count":12,"area":"lr"},{"id":"2510.04019","title":"Simple Policy Gradients for Reasoning with Diffusion Language Models","created":"2025-10-05","cited_by_count":12,"area":"lr"},{"id":"2601.10201","title":"Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization","created":"2026-01-15","cited_by_count":12,"area":"lr"},{"id":"2505.15311","title":"Trajectory Bellman Residual Minimization: A Simple Value-Based Method for LLM Reasoning","created":"2025-05-21","cited_by_count":11,"area":"lr"},{"id":"2506.18237","title":"AdapThink: Adaptive Thinking Preferences for Reasoning Language Model","created":"2025-06-23","cited_by_count":11,"area":"lr"},{"id":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2510.23049","title":"Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients","created":"2025-10-27","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":"2601.21968","title":"OVD: On-policy Verbal Distillation","created":"2026-01-29","cited_by_count":11,"area":"lr"},{"id":"2602.17550","title":"MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning","created":"2026-02-19","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":"2510.05251","title":"Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning","created":"2025-10-06","cited_by_count":10,"area":"lr"},{"id":"2510.02386","title":"On The Fragility of Benchmark Contamination Detection in Reasoning Models","created":"2025-09-30","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":"2602.21189","title":"Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training","created":"2026-02-24","cited_by_count":8,"area":"lr"},{"id":"2505.12992","title":"Fractured Chain-of-Thought 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":"2505.19501","title":"Toward Scientific Reasoning in LLMs: Training from Expert Discussions via Reinforcement Learning","created":"2025-05-26","cited_by_count":7,"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":"2506.04723","title":"Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning","created":"2025-06-05","cited_by_count":7,"area":"lr"},{"id":"2511.04800","title":"Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models","created":"2025-11-06","cited_by_count":7,"area":"lr"},{"id":"2511.05385","title":"TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework","created":"2025-11-07","cited_by_count":7,"area":"lr"},{"id":"2508.05928","title":"Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting","created":"2025-08-08","cited_by_count":6,"area":"lr"},{"id":"2510.11769","title":"GAR: Generative Adversarial Reinforcement Learning for Formal Theorem Proving","created":"2025-10-13","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":"2506.10343","title":"Code Execution as Grounded Supervision for LLM Reasoning","created":"2025-06-12","cited_by_count":5,"area":"lr"},{"id":"2508.07382","title":"Pentest-R1: Towards Autonomous Penetration Testing Reasoning Optimized via Two-Stage Reinforcement Learning","created":"2025-08-10","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":"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":"2511.07372","title":"Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2601.22448","title":"HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning","created":"2026-01-30","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":"2510.15979","title":"Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning","created":"2025-10-13","cited_by_count":3,"area":"lr"},{"id":"2602.00815","title":"Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement","created":"2026-01-31","cited_by_count":3,"area":"lr"},{"id":"2602.04391","title":"Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2604.28005","title":"Kernelized Advantage Estimation: From Nonparametric Statistics to LLM Reasoning","created":"2026-04-30","cited_by_count":3,"area":"lr"},{"id":"2506.10389","title":"EQA-RM: A Generative Embodied Reward Model with Test-time Scaling","created":"2025-06-12","cited_by_count":2,"area":"lr"},{"id":"2506.17913","title":"Learning, Reasoning, Refinement: A Framework for Kahneman's Dual-System Intelligence in GUI Agents","created":"2025-06-22","cited_by_count":2,"area":"lr"},{"id":"2508.11995","title":"AgentCDM: Enhancing Multi-Agent Collaborative Decision-Making via ACH-Inspired Structured Reasoning","created":"2025-08-16","cited_by_count":2,"area":"lr"},{"id":"2511.09865","title":"In-Token Rationality Optimization: Towards Accurate and Concise LLM Reasoning via Self-Feedback","created":"2025-11-13","cited_by_count":2,"area":"lr"},{"id":"2512.10430","title":"T-pro 2.0: An Efficient Russian Hybrid-Reasoning Model and Playground","created":"2025-12-11","cited_by_count":2,"area":"lr"},{"id":"2605.17003","title":"Learning-Zone Energy: Online Data Selection for Efficient RL Post-Training","created":"2026-05-16","cited_by_count":2,"area":"lr"},{"id":"2606.04560","title":"Rollout-Level Advantage-Prioritized Experience Replay for GRPO","created":"2026-06-03","cited_by_count":2,"area":"lr"},{"id":"2608.29622","title":"AgenticRag-R1: Agentic Reinforcement Learning with Stack Memory for Multi-Step Reasoning, Retrieval and Memorizing","created":"2026-08-30","cited_by_count":2,"area":"lr"},{"id":"2509.00768","title":"Aligning Reasoning LLMs for Materials Discovery with Physics-aware Rejection Sampling","created":"2025-08-31","cited_by_count":1,"area":"lr"},{"id":"2601.05616","title":"Dual-Phase LLM Reasoning: Self-Evolved Mathematical Frameworks","created":"2026-01-09","cited_by_count":1,"area":"lr"},{"id":"2601.14716","title":"PCL-Reasoner-V1.5: Advancing Math Reasoning with Offline Reinforcement Learning","created":"2026-01-21","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":"2604.26326","title":"Addressing Performance Saturation for LLM RL via Precise Entropy Curve Control","created":"2026-04-29","cited_by_count":1,"area":"lr"},{"id":"2605.02263","title":"Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning","created":"2026-05-04","cited_by_count":1,"area":"lr"},{"id":"2605.11505","title":"Selective Off-Policy Reference Tuning with Plan Guidance","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.20865","title":"Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards","created":"2026-05-20","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":"2510.14406","title":"IMAGINE: Integrating Multi-Agent System into One Model for Complex Reasoning and Planning","created":"2025-10-16","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":"2512.20169","title":"Learning to Reason in LLMs by Expectation Maximization","created":"2025-12-23","cited_by_count":0,"area":"lr"},{"id":"2601.21244","title":"Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2602.03516","title":"Not All Negative Samples Are Equal: LLMs Learn Better from Plausible Reasoning","created":"2026-02-03","cited_by_count":0,"area":"lr"},{"id":"2605.11726","title":"Block-R1: Rethinking the Role of Block Size in Multi-domain Reinforcement Learning for Diffusion Large Language Models","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2606.16154","title":"A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2606.22570","title":"What are Key Factors for Updates in RL for LLM Reasoning?","created":"2026-06-21","cited_by_count":0,"area":"lr"},{"id":"2609.32674","title":"Expected Reasoning-Step Return Unifies On-Policy Learning from Rewards and Teachers","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2610.03361","title":"Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFT","created":"2026-10-02","cited_by_count":0,"area":"lr"},{"id":"2610.07342","title":"Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding","created":"2026-10-05","cited_by_count":0,"area":"lr"}],"next_cursor":null}