{"total":80,"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":"2509.06941","title":"Outcome-based Exploration for LLM Reasoning","created":"2025-09-08","cited_by_count":83,"area":"lr"},{"id":"2509.15194","title":"Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation","created":"2025-09-18","cited_by_count":45,"area":null},{"id":"2510.20817","title":"KL-Regularized Reinforcement Learning is Designed to Mode Collapse","created":"2025-10-23","cited_by_count":31,"area":"deeprl"},{"id":"2509.26209","title":"Diversity-Incentivized Exploration for Versatile Reasoning","created":"2025-09-30","cited_by_count":28,"area":"lr"},{"id":"2601.14525","title":"Towards Execution-Grounded Automated AI Research","created":"2026-01-20","cited_by_count":28,"area":null},{"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":"2509.26522","title":"Entropy After </Think> for reasoning model early exiting","created":"2025-09-30","cited_by_count":24,"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":"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":"2510.02172","title":"RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization","created":"2025-10-02","cited_by_count":15,"area":"lr"},{"id":"2601.08763","title":"Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs","created":"2026-01-13","cited_by_count":12,"area":"lr"},{"id":"2510.21150","title":"String Seed of Thought: Prompting LLMs for Distribution-Faithful and Diverse Generation","created":"2025-10-24","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":"2602.01062","title":"SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2604.16027","title":"Where does output diversity collapse in post-training?","created":"2026-04-17","cited_by_count":11,"area":null},{"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":"2512.15687","title":"Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning","created":"2025-12-17","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":"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":"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":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2509.25424","title":"Polychromic Objectives for Reinforcement Learning","created":"2025-09-29","cited_by_count":7,"area":"deeprl"},{"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":"2602.03979","title":"Likelihood-Based Reward Designs for General LLM Reasoning","created":"2026-02-03","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":"2601.09609","title":"DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing","created":"2026-01-14","cited_by_count":6,"area":"lr"},{"id":"2603.15646","title":"Alternating Reinforcement Learning with Contextual Rubric Rewards: Beyond the Scalarization Strategy","created":"2026-03-04","cited_by_count":6,"area":"alignment"},{"id":"2603.21728","title":"EvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learning","created":"2026-03-23","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":"2510.01444","title":"Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"id":"2603.04597","title":"Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning","created":"2026-03-04","cited_by_count":5,"area":"lr"},{"id":"2603.04893","title":"Free Lunch for Pass@$k$? Low Cost Diverse Sampling for Diffusion Language Models","created":"2026-03-05","cited_by_count":5,"area":"diffusion"},{"id":"2604.17654","title":"Poly-EPO: Training Exploratory Reasoning Models","created":"2026-04-19","cited_by_count":5,"area":"lr"},{"id":"2509.23765","title":"Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality","created":"2025-09-28","cited_by_count":4,"area":"alignment"},{"id":"2606.07856","title":"Teacher-Free Self-Training Amplifies but Does Not Compound: A Pass@$K$ Crossover on a Free-Verifier Domain","created":"2026-06-05","cited_by_count":4,"area":"synth"},{"id":"2601.22629","title":"Time-Annealed Perturbation Sampling: Diverse Generation for Diffusion Language Models","created":"2026-01-30","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":"2604.27166","title":"Distributional Alignment Games for Answer-Level Fine-Tuning","created":"2026-04-29","cited_by_count":3,"area":"lr"},{"id":"2606.23595","title":"SPIRAL: Learning to Search and Aggregate","created":"2026-06-22","cited_by_count":3,"area":"lr"},{"id":"2607.12796","title":"The One-Word Census: Answer-Choice Conformity Across 105 Language Models","created":"2026-07-14","cited_by_count":3,"area":null},{"id":"2510.12699","title":"Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generations","created":"2025-10-14","cited_by_count":2,"area":null},{"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":"2604.18574","title":"When Can LLMs Learn to Reason with Weak Supervision?","created":"2026-04-20","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":"2606.03962","title":"Using Reward Uncertainty to Induce Diverse Behaviour in Reinforcement Learning","created":"2026-06-02","cited_by_count":2,"area":"alignment"},{"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":"2606.10346","title":"Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learning","created":"2026-06-09","cited_by_count":2,"area":"lr"},{"id":"2606.29985","title":"Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning","created":"2026-06-29","cited_by_count":2,"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":"2603.19044","title":"MoRI: Learning Motivation-Grounded Reasoning for Scientific Ideation in Large Language Models","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2604.03472","title":"Vocabulary Dropout for Curriculum Diversity in LLM Co-Evolution","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.07484","title":"ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training","created":"2026-04-08","cited_by_count":1,"area":"alignment"},{"id":"2605.06540","title":"Ex Ante Evaluation of AI-Induced Idea Diversity Collapse","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.11461","title":"Breaking $\\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.27130","title":"DEI: Diversity in Evolutionary Inference for Quality-Diversity Search","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2605.30021","title":"Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMs","created":"2026-05-28","cited_by_count":1,"area":"alignment"},{"id":"2607.08034","title":"PLURAL: A Global Dataset for Value Alignment","created":"2026-07-09","cited_by_count":1,"area":"alignment"},{"id":"2608.03467","title":"When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPO","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2609.13443","title":"Learning to Solve Hard Problems in RL for LLMs by Never Giving Up","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2510.03771","title":"OptAgent: Optimizing Query Rewriting for E-commerce via Multi-Agent Simulation","created":"2025-10-04","cited_by_count":0,"area":"agents"},{"id":"2512.12072","title":"VOYAGER: A Training Free Approach for Generating Diverse Datasets using LLMs","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2602.02862","title":"STEER: Inference-Time Risk Control via Constrained Quality-Diversity Search","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2604.11522","title":"Triviality Corrected Endogenous Reward","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.17314","title":"Weak-to-Strong Elicitation via Mismatched Wrong Drafts","created":"2026-05-17","cited_by_count":0,"area":"lr"},{"id":"2607.01849","title":"Decomposer: Learning to Decompile Symbolic Music to Programs","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.26862","title":"ReCo: Reweighting GRPO Against Distributional Concentration","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2609.00444","title":"Group Adaptive Clipping Policy Optimization","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.27374","title":"Planned Test-Time Scaling with Coordinated Reasoning Paths","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2609.31571","title":"Strategically Diverse Sampling for Self-Training","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.33038","title":"Improving the Diversity of LLM Outputs without a Trade-off","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.34718","title":"Quality Determines Direction, Length Shapes Magnitude: Length Control for Open-Ended Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2609.34929","title":"Sample What You Say: Aligning Language Models to Sample the Distributions They State","created":"2026-09-28","cited_by_count":0,"area":"alignment"},{"id":"2610.00661","title":"Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.01382","title":"Gacha Decoding: Eliciting Diverse Generations Through Instruction Following","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.06729","title":"Improving Diversity in LLM Short Story Generation","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.10536","title":"Decoupling Exploration from Optimization in RLVR","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}