{"total":138,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2509.06941","title":"Outcome-based Exploration for LLM Reasoning","created":"2025-09-08","cited_by_count":83,"area":"lr"},{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2511.15661","title":"VisPlay: Self-Evolving Vision-Language Models from Images","created":"2025-11-19","cited_by_count":47,"area":"lr"},{"id":"2509.07430","title":"The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward","created":"2025-09-09","cited_by_count":37,"area":null},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"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":"2510.11701","title":"Demystifying Reinforcement Learning in Agentic Reasoning","created":"2025-10-13","cited_by_count":33,"area":"lr"},{"id":"2509.26209","title":"Diversity-Incentivized Exploration for Versatile Reasoning","created":"2025-09-30","cited_by_count":28,"area":"lr"},{"id":"2602.13035","title":"Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL","created":"2026-02-13","cited_by_count":27,"area":null},{"id":"2511.19942","title":"Differential Smoothing Mitigates Sharpening and Improves LLM Reasoning","created":"2025-11-25","cited_by_count":22,"area":"lr"},{"id":"2603.24477","title":"Composer 2 Technical Report","created":"2026-03-25","cited_by_count":22,"area":"agents"},{"id":"2511.05993","title":"Revisiting Entropy in Reinforcement Learning for Large Reasoning Models","created":"2025-11-08","cited_by_count":21,"area":"lr"},{"id":"2602.07594","title":"Learning to Self-Verify Makes Language Models Better Reasoners","created":"2026-02-07","cited_by_count":21,"area":"lr"},{"id":"2509.23808","title":"Semantic-Space Exploration and Exploitation in RLVR for LLM Reasoning","created":"2025-09-28","cited_by_count":17,"area":"lr"},{"id":"2510.11686","title":"Representation-Based Exploration for Language Models: From Test-Time to Post-Training","created":"2025-10-13","cited_by_count":16,"area":null},{"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":"2605.10781","title":"Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR","created":"2026-05-11","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":"2510.05837","title":"EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget","created":"2025-10-07","cited_by_count":14,"area":null},{"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":"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":"2510.00911","title":"RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training","created":"2025-10-01","cited_by_count":12,"area":"lr"},{"id":"2510.08696","title":"Don't Waste Mistakes: Leveraging Negative RL-Groups via Confidence Reweighting","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2511.16231","title":"Pass@k Metric for RLVR: A Diagnostic Tool of Exploration, But Not an Objective","created":"2025-11-20","cited_by_count":12,"area":"lr"},{"id":"2602.03048","title":"CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs","created":"2026-02-03","cited_by_count":12,"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":"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":"2602.01062","title":"SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning","created":"2026-02-01","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":"2509.24981","title":"Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2510.03669","title":"Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning","created":"2025-10-04","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":"2510.11653","title":"MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model","created":"2025-10-13","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":"2606.26091","title":"On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity","created":"2026-06-24","cited_by_count":10,"area":"distill"},{"id":"2510.03199","title":"Best-of-Majority: Minimax-Optimal Strategy for Pass@$k$ Inference Scaling","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2510.04786","title":"Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning","created":"2025-10-06","cited_by_count":9,"area":"deeprl"},{"id":"2510.08325","title":"Beyond Pass@k: Breadth-Depth Metrics for Reasoning Boundaries","created":"2025-10-09","cited_by_count":9,"area":"lr"},{"id":"2512.02895","title":"MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm","created":"2025-12-02","cited_by_count":9,"area":"mllm"},{"id":"2602.19895","title":"DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning","created":"2026-02-23","cited_by_count":9,"area":"lr"},{"id":"2603.02045","title":"Expanding LLM Agent Boundaries with Strategy-Guided Exploration","created":"2026-03-02","cited_by_count":9,"area":"agents"},{"id":"2605.00365","title":"Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity","created":"2026-05-01","cited_by_count":9,"area":null},{"id":"2510.08892","title":"Exploring Multi-Temperature Strategies for Token- and Rollout-Level Control in RLVR","created":"2025-10-10","cited_by_count":8,"area":"lr"},{"id":"2512.01127","title":"Mode-Conditioning Unlocks Superior Test-Time Scaling","created":"2025-11-30","cited_by_count":8,"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":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2607.28568","title":"Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering","created":"2026-07-30","cited_by_count":8,"area":"synth"},{"id":"2510.04140","title":"Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs","created":"2025-10-05","cited_by_count":7,"area":"lr"},{"id":"2512.14754","title":"Revisiting the Reliability of Language Models in Instruction-Following","created":"2025-12-15","cited_by_count":7,"area":null},{"id":"2602.01705","title":"LaDi-RL: Latent Diffusion Reasoning Prevents Entropy Collapse in Reinforcement Learning","created":"2026-02-02","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":"2510.01143","title":"Generalized Parallel Scaling with Interdependent Generations","created":"2025-10-01","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":"2603.24844","title":"Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models","created":"2026-03-25","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":"2605.19461","title":"Beyond Mode Collapse: Distribution Matching for Diverse Reasoning","created":"2026-05-19","cited_by_count":6,"area":"lr"},{"id":"2510.20815","title":"Generative Reasoning Recommendation via LLMs","created":"2025-10-23","cited_by_count":5,"area":"lr"},{"id":"2510.26697","title":"The End of Manual Decoding: Towards Truly End-to-End Language Models","created":"2025-10-30","cited_by_count":5,"area":null},{"id":"2512.07558","title":"ReLaX: Reasoning with Latent Exploration for Large Reasoning Models","created":"2025-12-08","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":"2606.00151","title":"Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying","created":"2026-05-29","cited_by_count":5,"area":"deeprl"},{"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":"2602.11128","title":"Asymmetric Prompt Weighting for Reinforcement Learning with Verifiable Rewards","created":"2026-02-11","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":"2605.07039","title":"PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents","created":"2026-05-07","cited_by_count":4,"area":"agents"},{"id":"2605.20854","title":"Regret Analysis of Retry-Based Bandits","created":"2026-05-20","cited_by_count":4,"area":null},{"id":"2606.21090","title":"Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training","created":"2026-06-17","cited_by_count":4,"area":"lr"},{"id":"2607.27372","title":"Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation","created":"2026-07-29","cited_by_count":4,"area":null},{"id":"2510.02227","title":"More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration","created":"2025-10-02","cited_by_count":3,"area":"lr"},{"id":"2510.26109","title":"Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error","created":"2025-10-30","cited_by_count":3,"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":"2603.18886","title":"Reasoning over mathematical objects: on-policy reward modeling and test time aggregation","created":"2026-03-19","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":"2605.18864","title":"SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs","created":"2026-05-15","cited_by_count":3,"area":"lr"},{"id":"2609.02987","title":"Tail-Likelihood Reinforcement Learning","created":"2026-09-02","cited_by_count":3,"area":"deeprl"},{"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":"2510.15502","title":"The Road Less Traveled: Enhancing Exploration in LLMs via Sequential Sampling","created":"2025-10-17","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":"2601.04651","title":"Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"id":"2604.00860","title":"Policy Improvement Reinforcement Learning","created":"2026-04-01","cited_by_count":2,"area":"deeprl"},{"id":"2604.16995","title":"SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models","created":"2026-04-18","cited_by_count":2,"area":null},{"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":"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":"2605.08817","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":"2605.27000","title":"Cast a Wider Net: Coordinated Pass@K Policy Optimization for Code Reasoning","created":"2026-05-26","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":"2606.06080","title":"On Advantage Estimates for Max@K Policy Gradients","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2606.06096","title":"OrderGrad: Optimizing Beyond the Mean with Order-Statistic Policy Gradient Estimation","created":"2026-06-04","cited_by_count":2,"area":"deeprl"},{"id":"2607.14962","title":"Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation","created":"2026-07-16","cited_by_count":2,"area":"deeprl"},{"id":"2608.27420","title":"Boosting LLM Exploration via Weak-Model Guidance in RLVR","created":"2026-08-27","cited_by_count":2,"area":"lr"},{"id":"2512.06533","title":"Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning","created":"2025-12-06","cited_by_count":1,"area":"deeprl"},{"id":"2601.07238","title":"Group Pattern Selection Optimization: Let LRMs Pick the Right Pattern for Reasoning","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2602.04265","title":"Boosting LLM Reasoning via Human-Inspired Reward Shaping","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2602.06475","title":"Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning","created":"2026-02-06","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":"2602.22296","title":"UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs","created":"2026-02-25","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}