{"total":162,"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":"2507.14843","title":"The Invisible Leash: Why RLVR May or May Not Escape Its Origin","created":"2025-07-20","cited_by_count":97,"area":null},{"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":"2507.08794","title":"One Token to Fool LLM-as-a-Judge","created":"2025-07-11","cited_by_count":60,"area":"alignment"},{"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":"2509.25123","title":"From $f(x)$ and $g(x)$ to $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones","created":"2025-09-29","cited_by_count":42,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"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":"2509.25760","title":"TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning","created":"2025-09-30","cited_by_count":27,"area":null},{"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":"2510.14807","title":"Beyond the Sampled Token: Preserving Candidate Support in RLVR","created":"2025-10-16","cited_by_count":18,"area":null},{"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":"2510.23393","title":"The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation","created":"2025-10-27","cited_by_count":16,"area":null},{"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":"2602.22190","title":"GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL","created":"2026-02-25","cited_by_count":16,"area":"agents"},{"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":"2509.13333","title":"Evaluation Awareness Scales Predictably in Open-Weights Large Language Models","created":"2025-09-10","cited_by_count":14,"area":null},{"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":"2605.18703","title":"EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL","created":"2026-05-18","cited_by_count":14,"area":"agents"},{"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":"2511.15248","title":"EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control","created":"2025-11-19","cited_by_count":13,"area":null},{"id":"2509.19249","title":"Reinforcement Learning on Pre-Training Data","created":"2025-09-23","cited_by_count":12,"area":"lr"},{"id":"2509.21882","title":"Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards","created":"2025-09-26","cited_by_count":12,"area":null},{"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":"2608.31046","title":"Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement","created":"2026-08-31","cited_by_count":11,"area":"distill"},{"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":"2602.21158","title":"SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards","created":"2026-02-24","cited_by_count":9,"area":"agents"},{"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":"2606.08755","title":"Co-Evolving Skill Generation and Policy Optimization","created":"2026-06-07","cited_by_count":7,"area":null},{"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":"2508.21188","title":"Mirage or Method? How Model-Task Alignment Induces Divergent RL Conclusions","created":"2025-08-28","cited_by_count":6,"area":null},{"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":"2602.12036","title":"Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models","created":"2026-02-12","cited_by_count":6,"area":null},{"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":"2601.12186","title":"Aletheia: What Makes RLVR For Code Verifiers Tick?","created":"2026-01-17","cited_by_count":5,"area":null},{"id":"2602.05717","title":"Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2603.11219","title":"Senna-2: Aligning VLM and End-to-End Driving Policy for Consistent Decision Making and Planning","created":"2026-03-11","cited_by_count":5,"area":"mllm"},{"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":"2510.04695","title":"Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents","created":"2025-10-06","cited_by_count":4,"area":"agents"},{"id":"2510.06652","title":"Aligning Large Language Models via Fully Self-Synthetic Data","created":"2025-10-08","cited_by_count":4,"area":"alignment"},{"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":"2604.11446","title":"Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration","created":"2026-04-13","cited_by_count":4,"area":null},{"id":"2510.09596","title":"BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2510.18849","title":"Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning","created":"2025-10-21","cited_by_count":3,"area":"alignment"},{"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":"2601.06224","title":"Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization","created":"2026-01-09","cited_by_count":3,"area":"mllm"},{"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":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"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":"2605.00347","title":"Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning","created":"2026-05-01","cited_by_count":3,"area":"mllm"},{"id":"2605.08666","title":"The Cancellation Hypothesis in Critic-Free RL: From Outcome Rewards to Token Credits","created":"2026-05-09","cited_by_count":3,"area":null},{"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":"2605.12112","title":"When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy","created":"2026-05-12","cited_by_count":3,"area":"diffusion"},{"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":"2509.23595","title":"Timber: Training-free Instruct Model Refining with Base via Effective Rank","created":"2025-09-28","cited_by_count":2,"area":null},{"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":"2512.00778","title":"What Is Preference Optimization Doing, and Why?","created":"2025-11-30","cited_by_count":2,"area":"alignment"},{"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"}],"next_cursor":"100"}