{"total":113,"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":"2509.02479","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":"2507.08838","title":"wd1: Weighted Policy Optimization for Reasoning in Diffusion Language Models","created":"2025-07-07","cited_by_count":71,"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":"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":"2510.10150","title":"Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective","created":"2025-10-11","cited_by_count":52,"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":"2604.10688","title":"SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting","created":"2026-04-12","cited_by_count":43,"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":"2507.11407","title":"EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes","created":"2025-07-15","cited_by_count":32,"area":"lr"},{"id":"2506.20520","title":"Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards","created":"2025-06-25","cited_by_count":29,"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":"2510.01180","title":"BroRL: Scaling Reinforcement Learning via Broadened Exploration","created":"2025-10-01","cited_by_count":25,"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":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2511.05993","title":"Revisiting Entropy in Reinforcement Learning for Large Reasoning Models","created":"2025-11-08","cited_by_count":21,"area":"lr"},{"id":"2512.21625","title":"Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards","created":"2025-12-25","cited_by_count":19,"area":"lr"},{"id":"2510.02230","title":"The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models","created":"2025-10-02","cited_by_count":18,"area":"lr"},{"id":"2508.07534","title":"From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR","created":"2025-08-11","cited_by_count":17,"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":"2510.02172","title":"RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization","created":"2025-10-02","cited_by_count":15,"area":"lr"},{"id":"2509.24261","title":"Risk-Sensitive RL for Alleviating Exploration Dilemmas in Large Language Models","created":"2025-09-29","cited_by_count":14,"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":"2510.24302","title":"Lookahead Tree-Based Rollouts for Enhanced Trajectory-Level Exploration in Reinforcement Learning with Verifiable Rewards","created":"2025-10-28","cited_by_count":13,"area":"lr"},{"id":"2509.19249","title":"Reinforcement Learning on Pre-Training Data","created":"2025-09-23","cited_by_count":12,"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":"2510.08696","title":"Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2603.19880","title":"What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time","created":"2026-03-20","cited_by_count":12,"area":"lr"},{"id":"2507.19766","title":"UloRL:An Ultra-Long Output Reinforcement Learning Approach for Advancing Large Language Models' Reasoning Abilities","created":"2025-07-26","cited_by_count":11,"area":"lr"},{"id":"2509.22611","title":"Quantile Advantage Estimation: Stabilizing RLVR for LLM Reasoning","created":"2025-09-26","cited_by_count":11,"area":"lr"},{"id":"2601.18984","title":"Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning","created":"2026-01-26","cited_by_count":11,"area":"lr"},{"id":"2602.08499","title":"Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards","created":"2026-02-09","cited_by_count":11,"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":"2601.05053","title":"Reinforced Efficient Reasoning via Semantically Diverse Exploration","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2602.10520","title":"Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models","created":"2026-02-11","cited_by_count":8,"area":"lr"},{"id":"2604.11056","title":"Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR","created":"2026-04-13","cited_by_count":8,"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":"2601.15160","title":"Knowledge Graphs are Implicit Reward Models: Path-Derived Signals Enable Compositional Reasoning","created":"2026-01-21","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":"2606.23104","title":"ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation","created":"2026-06-22","cited_by_count":7,"area":"lr"},{"id":"2602.02555","title":"Learning to Explore with Parameter-Space Noise: A Deep Dive into Parameter-Space Noise for Reinforcement Learning with Verifiable Rewards","created":"2026-01-30","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":"2605.00380","title":"ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning","created":"2026-05-01","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":"2510.01444","title":"Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"id":"2601.04992","title":"Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization","created":"2026-01-08","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":"2510.26020","title":"PORTool: Importance-Aware Policy Optimization with Rewarded Tree for Multi-Tool-Integrated Reasoning","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2511.11373","title":"MarsRL: Advancing Multi-Agent Reasoning System via Reinforcement Learning with Agentic Pipeline Parallelism","created":"2025-11-14","cited_by_count":4,"area":"lr"},{"id":"2601.03661","title":"AMIR-GRPO: Inducing Implicit Preference Signals into GRPO","created":"2026-01-07","cited_by_count":4,"area":"lr"},{"id":"2603.16157","title":"DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon Replay","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2512.05962","title":"Whatever Remains Must Be True: Filtering Drives Reasoning in LLMs, Shaping Diversity","created":"2025-12-05","cited_by_count":3,"area":"lr"},{"id":"2601.20829","title":"Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning","created":"2026-01-28","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":"2602.04391","title":"Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical Reasoning","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2602.22751","title":"Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning","created":"2026-02-26","cited_by_count":3,"area":"lr"},{"id":"2604.14142","title":"From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space","created":"2026-04-15","cited_by_count":3,"area":"lr"},{"id":"2605.11491","title":"Understanding and Preventing Entropy Collapse in RLVR with On-Policy Entropy Flow Optimization","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2605.21468","title":"You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories","created":"2026-05-20","cited_by_count":3,"area":"lr"},{"id":"2606.19236","title":"STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability","created":"2026-06-17","cited_by_count":3,"area":"lr"},{"id":"2606.31575","title":"Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index","created":"2026-06-30","cited_by_count":3,"area":"lr"},{"id":"2609.20807","title":"Score Centering Stabilizes Off-policy Reinforcement Learning","created":"2026-09-17","cited_by_count":3,"area":"lr"},{"id":"2508.09521","title":"PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning","created":"2025-08-13","cited_by_count":2,"area":"lr"},{"id":"2511.18305","title":"DiVE-k: Differential Visual Reasoning for Fine-grained Image Recognition","created":"2025-11-23","cited_by_count":2,"area":"lr"},{"id":"2601.09085","title":"MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2602.03452","title":"Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional Pairing","created":"2026-02-03","cited_by_count":2,"area":"lr"},{"id":"2602.05281","title":"Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities","created":"2026-02-05","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":"2603.00889","title":"CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning","created":"2026-03-01","cited_by_count":2,"area":"lr"},{"id":"2603.16223","title":"Dual Consensus: Escaping from Spurious Majority in Unsupervised RLVR via Two-Stage Vote Mechanism","created":"2026-03-17","cited_by_count":2,"area":"lr"},{"id":"2604.18493","title":"Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data","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":"2605.05826","title":"AGPO: Asymmetric Group Policy Optimization for Verifiable Reasoning and Search Ads Relevance at JD","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2605.08817","title":"How You Begin is How You Reason: Driving Exploration in RLVR via Prefix-Tuned Priors","created":"2026-05-09","cited_by_count":2,"area":"lr"},{"id":"2605.28295","title":"Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR","created":"2026-05-27","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"},{"id":"2511.04439","title":"CoRPO: Adding a Correctness Bias to GRPO Improves Generalization","created":"2025-11-06","cited_by_count":1,"area":"lr"},{"id":"2512.22955","title":"Diversity or Precision? A Deep Dive into Next Token Prediction","created":"2025-12-28","cited_by_count":1,"area":"lr"},{"id":"2601.21476","title":"Thinking Seeds: Leveraging Historical Diversity for Position-Aware RL in LLMs","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.12642","title":"Beyond Normalization: Rethinking the Partition Function as a Difficulty Scheduler for RLVR","created":"2026-02-13","cited_by_count":1,"area":"lr"},{"id":"2604.04894","title":"Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2604.18235","title":"Negative Advantages Is a Double-Edged Sword: Calibrating advantages in GRPO for Search Agents","created":"2026-04-20","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":"2605.00754","title":"Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring","created":"2026-05-01","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":"2605.07137","title":"Adaptive Negative Reinforcement for LLM Reasoning:Dynamically Balancing Correction and Diversity in RLVR","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.16342","title":"DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models","created":"2026-05-08","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":"2605.22703","title":"Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals","created":"2026-05-21","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":"2510.21830","title":"GAPO: Robust Advantage Estimation for Real-World Code LLMs","created":"2025-10-22","cited_by_count":0,"area":"lr"},{"id":"2512.02580","title":"From Imitation to Discrimination: Toward A Generalized Curriculum Advantage Mechanism Enhancing Cross-Domain Reasoning Tasks","created":"2025-12-02","cited_by_count":0,"area":"lr"},{"id":"2601.21192","title":"Do Reasoning Models Enhance Embedding Models?","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2602.11748","title":"Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning","created":"2026-02-12","cited_by_count":0,"area":"lr"},{"id":"2603.23355","title":"Off-Policy Value-Based Reinforcement Learning for Large Language Models","created":"2026-03-24","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":"2605.15012","title":"Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2605.18903","title":"Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era","created":"2026-05-17","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}