{"total":89,"rows":[{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"id":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2604.03128","title":"Self-Distilled RLVR","created":"2026-04-03","cited_by_count":131,"area":"distill"},{"id":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111,"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":"2510.02245","title":"ExGRPO: Learning to Reason from Experience","created":"2025-10-02","cited_by_count":53,"area":"lr"},{"id":"2509.09265","title":"Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents","created":"2025-09-11","cited_by_count":46,"area":"agents"},{"id":"2509.03646","title":"Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning","created":"2025-09-03","cited_by_count":42,"area":"lr"},{"id":"2507.21848","title":"EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity","created":"2025-07-29","cited_by_count":41,"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":"2510.10649","title":"Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning","created":"2025-10-12","cited_by_count":34,"area":"lr"},{"id":"2508.09138","title":"Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models","created":"2025-08-12","cited_by_count":33,"area":"diffusion"},{"id":"2505.24718","title":"Reinforcing Video Reasoning with Focused Thinking","created":"2025-05-30","cited_by_count":31,"area":"lr"},{"id":"2508.02260","title":"Decomposing the Entropy-Performance Exchange: The Missing Keys to Unlocking Effective Reinforcement Learning","created":"2025-08-04","cited_by_count":21,"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":"2510.01833","title":"Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning","created":"2025-10-02","cited_by_count":19,"area":"lr"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2506.22200","title":"EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework","created":"2025-06-27","cited_by_count":14,"area":"lr"},{"id":"2510.26374","title":"BOTS: A Unified Framework for Bayesian Online Task Selection in LLM Reinforcement Finetuning","created":"2025-10-30","cited_by_count":14,"area":"alignment"},{"id":"2605.19447","title":"What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents","created":"2026-05-19","cited_by_count":13,"area":"agents"},{"id":"2508.10316","title":"Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances","created":"2025-08-14","cited_by_count":12,"area":"deeprl"},{"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":"2510.24832","title":"Scheduling Your LLM Reinforcement Learning with Reasoning Trees","created":"2025-10-28","cited_by_count":12,"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":"2509.18849","title":"MAPO: Mixed Advantage Policy Optimization","created":"2025-09-23","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":"2507.06829","title":"Adaptive Termination for Multi-round Parallel Reasoning: An Universal Semantic Entropy-Guided Framework","created":"2025-07-09","cited_by_count":10,"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":"2606.05152","title":"Reinforcement Learning from Rich Feedback with Distributional DAgger","created":"2026-06-03","cited_by_count":10,"area":"lr"},{"id":"2606.15866","title":"STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning","created":"2026-06-14","cited_by_count":10,"area":"lr"},{"id":"2509.21792","title":"FastGRPO: Accelerating Policy Optimization via Concurrency-aware Speculative Decoding and Online Draft Learning","created":"2025-09-26","cited_by_count":9,"area":"lr"},{"id":"2601.03823","title":"Step Potential Advantage Estimation: Harnessing Intermediate Confidence and Correctness for Efficient Mathematical Reasoning","created":"2026-01-07","cited_by_count":9,"area":"lr"},{"id":"2603.22847","title":"Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought","created":"2026-03-24","cited_by_count":9,"area":"lr"},{"id":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","cited_by_count":9,"area":"lr"},{"id":"2606.04036","title":"Self-Distilled Policy Gradient","created":"2026-06-02","cited_by_count":8,"area":"lr"},{"id":"2602.07595","title":"TeleBoost: A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation","created":"2026-02-07","cited_by_count":7,"area":null},{"id":"2605.21801","title":"Why Semantic Entropy Fails: Geometry-Aware and Calibrated Uncertainty for Policy Optimization","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2508.05928","title":"Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting","created":"2025-08-08","cited_by_count":6,"area":"lr"},{"id":"2602.05535","title":"Detecting Misbehaviors of Large Vision-Language Models by Evidential Uncertainty Quantification","created":"2026-02-05","cited_by_count":6,"area":"mllm"},{"id":"2511.07738","title":"From Exploration to Exploitation: A Two-Stage Entropy RLVR Approach for Noise-Tolerant MLLM Training","created":"2025-11-11","cited_by_count":5,"area":"mllm"},{"id":"2602.06825","title":"AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models","created":"2026-02-06","cited_by_count":5,"area":"diffusion"},{"id":"2602.23802","title":"EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models","created":"2026-02-27","cited_by_count":5,"area":"lr"},{"id":"2603.10101","title":"CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR","created":"2026-03-10","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2512.08511","title":"Thinking with Images via Self-Calling Agent","created":"2025-12-09","cited_by_count":4,"area":"lr"},{"id":"2601.04700","title":"PRISM: A Unified Framework for Post-Training LLMs Without Verifiable Rewards","created":"2026-01-08","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":"2604.25591","title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","created":"2026-04-28","cited_by_count":4,"area":null},{"id":"2605.04984","title":"Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2606.08501","title":"Back on Track: Aligning Rewards and States for Reasoning in Diffusion Large Language Models","created":"2026-06-07","cited_by_count":4,"area":"lr"},{"id":"2606.32032","title":"Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs","created":"2026-06-30","cited_by_count":4,"area":"alignment"},{"id":"2509.23962","title":"Conditional Advantage Estimation for Reinforcement Learning in Large Reasoning Models","created":"2025-09-28","cited_by_count":3,"area":"lr"},{"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":"2602.00815","title":"Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement","created":"2026-01-31","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":"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":"2605.02178","title":"T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning","created":"2026-05-04","cited_by_count":3,"area":"lr"},{"id":"2605.08441","title":"DUET: Optimize Token-Budget Allocation for Reinforcement Learning with Verifiable Rewards","created":"2026-05-08","cited_by_count":3,"area":null},{"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":"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":"2509.24560","title":"AdaThink-Med: Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty Quantification","created":"2025-09-29","cited_by_count":2,"area":"lr"},{"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":"2511.06380","title":"What Makes Reasoning Invalid: Echo Reflection Mitigation for Large Language Models","created":"2025-11-09","cited_by_count":2,"area":"lr"},{"id":"2511.09865","title":"In-Token Rationality Optimization: Towards Accurate and Concise LLM Reasoning via Self-Feedback","created":"2025-11-13","cited_by_count":2,"area":"lr"},{"id":"2606.08543","title":"PAEC: Position-Aware Entropy Calibration for LLM Reasoning in RLVR","created":"2026-06-07","cited_by_count":2,"area":"lr"},{"id":"2601.06911","title":"Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models","created":"2026-01-11","cited_by_count":1,"area":null},{"id":"2601.22478","title":"Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2601.22521","title":"One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.03190","title":"PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2602.10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2605.27293","title":"BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning","created":"2026-05-26","cited_by_count":1,"area":"lr"},{"id":"2606.03094","title":"FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2608.30632","title":"GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning","created":"2026-08-31","cited_by_count":1,"area":"lr"},{"id":"2506.13358","title":"Socratic RL: A Novel Framework for Efficient Knowledge Acquisition through Iterative Reflection and Viewpoint Distillation","created":"2025-06-16","cited_by_count":0,"area":"distill"},{"id":"2509.25941","title":"Boosting Process-Correct CoT Reasoning by Modeling Solvability of Multiple-Choice QA","created":"2025-09-30","cited_by_count":0,"area":"lr"},{"id":"2510.27410","title":"Closing the Expression Gap in LLM Instructions via Socratic Questioning","created":"2025-10-31","cited_by_count":0,"area":null},{"id":"2601.07298","title":"Mimic Human Cognition, Master Multi-Image Reasoning: A Meta-Action Framework for Enhanced Visual Understanding","created":"2026-01-12","cited_by_count":0,"area":"lr"},{"id":"2603.16929","title":"MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning","created":"2026-03-14","cited_by_count":0,"area":"deeprl"},{"id":"2604.11510","title":"Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2604.17928","title":"HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment","created":"2026-04-20","cited_by_count":0,"area":"lr"},{"id":"2605.08186","title":"Rethinking Entropy Minimization in Test-Time Adaptation for Autoregressive Models","created":"2026-05-05","cited_by_count":0,"area":"lr"},{"id":"2605.12058","title":"Holder Policy Optimisation","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2606.11634","title":"Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math Reasoning","created":"2026-06-10","cited_by_count":0,"area":"lr"},{"id":"2606.22570","title":"What are Key Factors for Updates in RL for LLM Reasoning?","created":"2026-06-21","cited_by_count":0,"area":"lr"},{"id":"2606.26917","title":"GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.18915","title":"Reasoning Error from Known Fact: Step-Level Self-Consistency Group Relative Policy Optimization for LLM","created":"2026-07-21","cited_by_count":0,"area":"lr"},{"id":"2608.17411","title":"GUPO: Gradient Uncertainty-aware Policy Optimization for Post-Training Large Language Models","created":"2026-08-18","cited_by_count":0,"area":"lr"},{"id":"2609.32674","title":"Expected Reasoning-Step Return Unifies On-Policy Learning from Rewards and Teachers","created":"2026-09-26","cited_by_count":0,"area":"lr"}],"next_cursor":null}