{"total":148,"rows":[{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281,"area":"lr"},{"id":"2405.10292","title":"Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning","created":"2024-05-16","cited_by_count":158,"area":"lr"},{"id":"2404.10642","title":"Self-playing Adversarial Language Game Enhances LLM Reasoning","created":"2024-04-16","cited_by_count":83,"area":"lr"},{"id":"2503.16252","title":"Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning","created":"2025-03-20","cited_by_count":83,"area":"lr"},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79,"area":"lr"},{"id":"2510.05592","title":"In-the-Flow Agentic System Optimization for Effective Planning and Tool Use","created":"2025-10-07","cited_by_count":72,"area":"lr"},{"id":"2412.10400","title":"Reinforcement Learning Enhanced LLMs: A Survey","created":"2024-12-05","cited_by_count":71,"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":"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":"2511.06449","title":"FLEX: Continuous Agent Evolution via Forward Learning from Experience","created":"2025-11-09","cited_by_count":52,"area":"lr"},{"id":"2405.14314","title":"Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration","created":"2024-05-23","cited_by_count":45,"area":"lr"},{"id":"2507.02841","title":"StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason","created":"2025-07-03","cited_by_count":39,"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":"2508.18588","title":"History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL","created":"2025-08-26","cited_by_count":38,"area":"lr"},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37,"area":"lr"},{"id":"2602.04879","title":"Rethinking the Trust Region in LLM Reinforcement Learning","created":"2026-02-04","cited_by_count":37,"area":"lr"},{"id":"2505.22257","title":"Revisiting Group Relative Policy Optimization: Insights into On-Policy and Off-Policy Training","created":"2025-05-28","cited_by_count":34,"area":"lr"},{"id":"2301.00355","title":"Second Thoughts are Best: Learning to Re-Align With Human Values from Text Edits","created":"2023-01-01","cited_by_count":27,"area":"lr"},{"id":"2509.21474","title":"d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation","created":"2025-09-25","cited_by_count":27,"area":"lr"},{"id":"2510.00977","title":"It Takes Two: Your GRPO Is Secretly DPO","created":"2025-10-01","cited_by_count":26,"area":"lr"},{"id":"2606.22600","title":"On the Position Bias of On-Policy Distillation","created":"2026-06-21","cited_by_count":26,"area":"lr"},{"id":"2510.01180","title":"BroRL: Scaling Reinforcement Learning via Broadened Exploration","created":"2025-10-01","cited_by_count":25,"area":"lr"},{"id":"2507.04742","title":"Activation Steering for Chain-of-Thought Compression","created":"2025-07-07","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":"2510.08233","title":"Enhancing Reasoning for Diffusion LLMs via Distribution Matching Policy Optimization","created":"2025-10-09","cited_by_count":20,"area":"lr"},{"id":"2604.06268","title":"RAGEN-2: Reasoning Collapse in Agentic RL","created":"2026-04-07","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":"2505.16826","title":"KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning","created":"2025-05-22","cited_by_count":19,"area":"lr"},{"id":"2508.03772","title":"GTPO: Stabilizing Group Relative Policy Optimization via Gradient and Entropy Control","created":"2025-08-05","cited_by_count":18,"area":"lr"},{"id":"2510.26475","title":"ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems","created":"2025-10-30","cited_by_count":18,"area":"lr"},{"id":"2602.04663","title":"Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design","created":"2026-02-04","cited_by_count":17,"area":"lr"},{"id":"2508.17784","title":"Proximal Supervised Fine-Tuning","created":"2025-08-25","cited_by_count":16,"area":"lr"},{"id":"2603.21872","title":"Manifold-Aware Exploration for Reinforcement Learning in Video Generation","created":"2026-03-23","cited_by_count":15,"area":"lr"},{"id":"2507.06892","title":"Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model","created":"2025-07-09","cited_by_count":14,"area":"lr"},{"id":"2509.01684","title":"Reinforcement Learning for Machine Learning Engineering Agents","created":"2025-09-01","cited_by_count":14,"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":"2510.00911","title":"RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training","created":"2025-10-01","cited_by_count":12,"area":"lr"},{"id":"2510.26491","title":"Data-Efficient RLVR via Off-Policy Influence Guidance","created":"2025-10-30","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":"2505.15447","title":"ViaRL: Adaptive Temporal Grounding via Visual Iterated Amplification Reinforcement Learning","created":"2025-05-21","cited_by_count":11,"area":"lr"},{"id":"2509.16742","title":"Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories","created":"2025-09-20","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":"2603.11682","title":"Entropy-Preserving Reinforcement Learning","created":"2026-03-12","cited_by_count":11,"area":"lr"},{"id":"2603.06743","title":"Stabilizing Reinforcement Learning for Diffusion Language Models","created":"2026-03-06","cited_by_count":10,"area":"lr"},{"id":"2603.21563","title":"Counterfactual Credit Policy Optimization for Multi-Agent Collaboration","created":"2026-03-23","cited_by_count":10,"area":"lr"},{"id":"2606.05152","title":"Reinforcement Learning from Rich Feedback with Distributional DAgger","created":"2026-06-03","cited_by_count":10,"area":"lr"},{"id":"2506.07160","title":"GeometryZero: Advancing Geometry Solving via Group Contrastive Policy Optimization","created":"2025-06-08","cited_by_count":9,"area":"lr"},{"id":"2602.15620","title":"STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens","created":"2026-02-17","cited_by_count":9,"area":"lr"},{"id":"2411.00773","title":"LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation","created":"2024-11-01","cited_by_count":8,"area":"lr"},{"id":"2505.14585","title":"Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2602.13953","title":"QuRL: Efficient Reinforcement Learning with Quantized Rollout","created":"2026-02-15","cited_by_count":8,"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":"2505.23816","title":"A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMs","created":"2025-05-27","cited_by_count":7,"area":"lr"},{"id":"2509.21282","title":"It's Not You, It's Clipping: A Soft Trust-Region via Probability Smoothing for LLM RL","created":"2025-09-25","cited_by_count":7,"area":"lr"},{"id":"2511.03527","title":"Learning Without Critics? Revisiting GRPO in Classical Reinforcement Learning Environments","created":"2025-11-05","cited_by_count":6,"area":"lr"},{"id":"2601.03320","title":"Ratio-Variance Regularized Policy Optimization for Efficient LLM Fine-tuning","created":"2026-01-06","cited_by_count":6,"area":"lr"},{"id":"2603.14389","title":"From $\\log \\pi$ to $\\pi$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2509.24050","title":"Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training","created":"2025-09-28","cited_by_count":5,"area":"lr"},{"id":"2510.20815","title":"Generative Reasoning Recommendation via LLMs","created":"2025-10-23","cited_by_count":5,"area":"lr"},{"id":"2511.18919","title":"Learning What to Trust: Bayesian Prior-Guided Optimization for Visual Generation","created":"2025-11-24","cited_by_count":5,"area":"lr"},{"id":"2602.04417","title":"EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL","created":"2026-02-04","cited_by_count":5,"area":"lr"},{"id":"2604.17654","title":"Poly-EPO: Training Exploratory Reasoning Models","created":"2026-04-19","cited_by_count":5,"area":"lr"},{"id":"2606.09821","title":"Rethinking the Divergence Regularization in LLM RL","created":"2026-06-08","cited_by_count":5,"area":"lr"},{"id":"2508.20018","title":"SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control","created":"2025-08-27","cited_by_count":4,"area":"lr"},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","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":"2605.31228","title":"EchoRL: Reinforcement Learning via Rollout Echoing","created":"2026-05-29","cited_by_count":4,"area":"lr"},{"id":"2608.23566","title":"Best Practice Critic Optimization","created":"2026-08-24","cited_by_count":4,"area":"lr"},{"id":"2202.12162","title":"Measuring CLEVRness: Blackbox testing of Visual Reasoning Models","created":"2022-02-24","cited_by_count":3,"area":"lr"},{"id":"2504.18587","title":"An Expectation-Maximization Perspective on Reinforcement Learning for LLM Reasoning","created":"2025-04-24","cited_by_count":3,"area":"lr"},{"id":"2505.03181","title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making","created":"2025-05-06","cited_by_count":3,"area":"lr"},{"id":"2506.00845","title":"Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment","created":"2025-06-01","cited_by_count":3,"area":"lr"},{"id":"2509.23183","title":"ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse","created":"2025-09-27","cited_by_count":3,"area":"lr"},{"id":"2510.09369","title":"Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2602.04620","title":"QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning","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":"2603.01563","title":"LFPO: Likelihood-Free Policy Optimization for Masked Diffusion Models","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2606.10968","title":"Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning","created":"2026-06-09","cited_by_count":3,"area":"lr"},{"id":"2607.10169","title":"Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization","created":"2026-07-11","cited_by_count":3,"area":"lr"},{"id":"2607.15200","title":"Mask-Aware Policy Gradients for Diffusion Language Models","created":"2026-07-16","cited_by_count":3,"area":"lr"},{"id":"2503.19523","title":"One Framework to Rule Them All: Unifying RL-Based and RL-Free Methods in RLHF","created":"2025-03-25","cited_by_count":2,"area":"lr"},{"id":"2510.11278","title":"ENIGMA: The Geometry of Reasoning and Alignment in Large-Language Models","created":"2025-10-13","cited_by_count":2,"area":"lr"},{"id":"2510.18814","title":"A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning","created":"2025-10-21","cited_by_count":2,"area":"lr"},{"id":"2511.15256","title":"GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning","created":"2025-11-19","cited_by_count":2,"area":"lr"},{"id":"2512.15089","title":"Beyond Fast and Slow: Cognitive-Inspired Elastic Reasoning for Large Language Models","created":"2025-12-17","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":"2602.00085","title":"CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":"lr"},{"id":"2602.20132","title":"LAD: Learning Advantage Distribution for Reasoning","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2603.20899","title":"Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach","created":"2026-03-21","cited_by_count":2,"area":"lr"},{"id":"2605.05802","title":"Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2605.06523","title":"On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2605.22156","title":"One-Way Policy Optimization for Self-Evolving LLMs","created":"2026-05-21","cited_by_count":2,"area":"lr"},{"id":"2605.28184","title":"Joint Training of Multi-Token Prediction in Reinforcement Learning via Optimal Coefficient Calibration","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.07950","title":"The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning","created":"2026-06-06","cited_by_count":2,"area":"lr"},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2607.06855","title":"Geometric Self-Distillation for Reasoning Generalization","created":"2026-07-07","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}