{"total":27,"rows":[{"id":"2510.10150","title":"Rethinking Entropy Interventions in RLVR: An Entropy Change Perspective","created":"2025-10-11","cited_by_count":52,"area":"lr"},{"id":"2510.23497","title":"VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation","created":"2025-10-27","cited_by_count":31,"area":"lr"},{"id":"2602.08499","title":"Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards","created":"2026-02-09","cited_by_count":11,"area":"lr"},{"id":"2602.17550","title":"MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning","created":"2026-02-19","cited_by_count":11,"area":"lr"},{"id":"2512.00499","title":"ESPO: Entropy Importance Sampling Policy Optimization","created":"2025-11-29","cited_by_count":9,"area":"lr"},{"id":"2511.04800","title":"Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models","created":"2025-11-06","cited_by_count":7,"area":"lr"},{"id":"2601.22718","title":"A Step Back: Prefix Importance Ratio Stabilizes Policy Optimization","created":"2026-01-30","cited_by_count":7,"area":"lr"},{"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":"2605.21125","title":"Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation","created":"2026-05-20","cited_by_count":7,"area":"lr"},{"id":"2510.00819","title":"Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning","created":"2025-10-01","cited_by_count":5,"area":"lr"},{"id":"2510.15990","title":"Can GRPO Help LLMs Transcend Their Pretraining Origin?","created":"2025-10-14","cited_by_count":5,"area":"lr"},{"id":"2511.04256","title":"SSPO: Subsentence-level Policy Optimization","created":"2025-11-06","cited_by_count":5,"area":"lr"},{"id":"2512.07558","title":"ReLaX: Reasoning with Latent Exploration for Large Reasoning Models","created":"2025-12-08","cited_by_count":5,"area":"lr"},{"id":"2510.08899","title":"Pinpointing crucial steps: Attribution-based Credit Assignment for Verifiable Reinforcement Learning","created":"2025-10-10","cited_by_count":4,"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":"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":"2602.05281","title":"Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2602.10880","title":"Chart Specification: Structural Representations for Incentivizing VLM Reasoning in Chart-to-Code Generation","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"id":"2604.08690","title":"Skip-Connected Policy Optimization for Implicit Advantage","created":"2026-04-09","cited_by_count":1,"area":"lr"},{"id":"2604.16972","title":"MCPO: Mastery-Consolidated Policy Optimization for Large Reasoning Models","created":"2026-04-18","cited_by_count":1,"area":"lr"},{"id":"2604.23318","title":"Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance","created":"2026-04-25","cited_by_count":1,"area":"lr"},{"id":"2605.28388","title":"Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.16733","title":"A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2602.05494","title":"A Unified Framework for Rethinking Policy Divergence Measures in GRPO","created":"2026-02-05","cited_by_count":0,"area":"lr"},{"id":"2604.13088","title":"Design Conditions for Intra-Group Learning of Sequence-Level Rewards: Token Gradient Cancellation","created":"2026-04-04","cited_by_count":0,"area":"lr"},{"id":"2610.13015","title":"Generalized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of Divergence","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.13020","title":"Trajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RL","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}