{"total":44,"rows":[{"id":"2509.02534","title":"Jointly Reinforcing Diversity and Quality in Language Model Generations","created":"2025-09-02","cited_by_count":80,"area":null},{"id":"2510.18927","title":"BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping","created":"2025-10-21","cited_by_count":47,"area":null},{"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":"2508.11356","title":"ETTRL: Balancing Exploration and Exploitation in LLM Test-Time Reinforcement Learning Via Entropy Mechanism","created":"2025-08-15","cited_by_count":36,"area":null},{"id":"2512.02472","title":"Guided Self-Evolving LLMs with Minimal Human Supervision","created":"2025-12-02","cited_by_count":35,"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":"2508.14496","title":"Semantic Energy: Detecting LLM Hallucination Beyond Entropy","created":"2025-08-20","cited_by_count":18,"area":null},{"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":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"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":"2509.16591","title":"Heterogeneous Adaptive Policy Optimization: Tailoring Optimization to Every Token's Nature","created":"2025-09-20","cited_by_count":11,"area":null},{"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":"2511.05650","title":"Optimizing Diversity and Quality through Base-Aligned Model Collaboration","created":"2025-11-07","cited_by_count":8,"area":null},{"id":"2510.09259","title":"Detecting Data Contamination from Reinforcement Learning Post-training for Large Language Models","created":"2025-10-10","cited_by_count":6,"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":"2510.08549","title":"Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2601.15609","title":"When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards","created":"2026-01-22","cited_by_count":4,"area":null},{"id":"2507.13874","title":"Geometry of Knowledge Allows Extending Diversity Boundaries of Large Language Models","created":"2025-07-18","cited_by_count":3,"area":null},{"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":"2605.11775","title":"Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2607.16850","title":"Group Entropy-Controlled Policy Optimization","created":"2026-07-18","cited_by_count":3,"area":null},{"id":"2601.03725","title":"EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2602.00513","title":"Minerva: Reinforcement Learning with Verifiable Rewards for Cyber Threat Intelligence LLMs","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2603.24093","title":"Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalization","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2607.07646","title":"RL Post-Training Builds Compositional Reasoning Strategies","created":"2026-07-08","cited_by_count":2,"area":null},{"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":"2601.12730","title":"Distribution-Centric Policy Optimization Dominates Exploration-Exploitation Trade-off","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2601.23006","title":"InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuning","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2604.11297","title":"The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2605.29303","title":"Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2607.14614","title":"Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2601.22532","title":"Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.20723","title":"Modality-Guided Mixture of Structured Experts with Entropy-Triggered Routing for Multimodal Recommendation","created":"2026-02-24","cited_by_count":0,"area":null},{"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":"2605.11328","title":"Epistemic Uncertainty for Test-Time Discovery","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.17295","title":"DISA: Offline Importance Sampling for Distribution-Matching LLM-RL","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.25381","title":"Not only where, But when: Temporal Scheduling for RLVR","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.28109","title":"Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.27369","title":"Reinforcement Learning without Ground-Truth Solutions can Improve LLMs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.01804","title":"LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.20715","title":"Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.31688","title":"Don't Repeat Yourself: Self-Supervised Fine-Tuning for Coverage","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.33589","title":"TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}