{"total":36,"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":"2510.08141","title":"SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training","created":"2025-10-09","cited_by_count":12,"area":"lr"},{"id":"2512.00908","title":"Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs","created":"2025-11-30","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":"2511.11113","title":"VIDEOP2R: Video Understanding from Perception to Reasoning","created":"2025-11-14","cited_by_count":8,"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":"2605.21125","title":"Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation","created":"2026-05-20","cited_by_count":7,"area":"lr"},{"id":"2510.08026","title":"PEAR: Phase Entropy Aware Reward for Efficient Reasoning","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2602.05165","title":"EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization","created":"2026-02-05","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":"2604.08905","title":"StaRPO: Stability-Augmented Reinforcement Policy Optimization","created":"2026-04-10","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":"2512.13070","title":"M-GRPO: Stabilizing Self-Supervised Reinforcement Learning for Large Language Models with Momentum-Anchored Policy Optimization","created":"2025-12-15","cited_by_count":4,"area":"lr"},{"id":"2602.22642","title":"Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning","created":"2026-02-26","cited_by_count":4,"area":"lr"},{"id":"2510.03259","title":"Verifying Meta-Awareness via Predictive Rewards in Reasoning Models","created":"2025-09-26","cited_by_count":3,"area":"lr"},{"id":"2602.22751","title":"Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning","created":"2026-02-26","cited_by_count":3,"area":"lr"},{"id":"2603.10359","title":"HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"id":"2605.17333","title":"Leveraging Error Diversity in Group Rollouts for Reinforcement Learning","created":"2026-05-17","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":"2601.07695","title":"Smooth Operator: Smooth Verifiable Reward Activates Spatial Reasoning Ability of Vision-Language Model","created":"2026-01-12","cited_by_count":2,"area":"lr"},{"id":"2606.03021","title":"Hint-Guided Diversified Policy Optimization for LLM Reasoning","created":"2026-06-02","cited_by_count":2,"area":"lr"},{"id":"2608.17423","title":"Prism-GRPO: Faster VLA Policy Optimization via Splitting Same-outcome Groups","created":"2026-08-18","cited_by_count":2,"area":"lr"},{"id":"2609.11699","title":"Negative Self-Distillation: Learning to Reason by Avoiding Flaws","created":"2026-09-10","cited_by_count":2,"area":"lr"},{"id":"2603.29871","title":"ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training","created":"2026-03-31","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":"2605.30789","title":"Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"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":"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":"2605.25511","title":"CRPO: Character-centric Group Relative Policy Optimization for Role-aware Reasoning in Role-playing Agents","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2606.05800","title":"SALT: When More Rollouts Don't Help in Group-Based Policy Optimization and How to Make Them Matter","created":"2026-06-04","cited_by_count":0,"area":"lr"},{"id":"2606.29812","title":"Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning","created":"2026-06-29","cited_by_count":0,"area":"lr"},{"id":"2608.28771","title":"ERR+: Sequential Entropy Resolution for Efficient and Decisive LLM Reasoning","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.04063","title":"Spurious Advantage Hidden in GRPO","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.25773","title":"Video-HopChain: Multi-Hop Questions and Confidence-Gated Exploration for Video Reasoning Models","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.36804","title":"VAA-CSEC: Vote-guided Advantage Allocation for Chinese Semantic Error Correction","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.39402","title":"Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy Optimization","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":null}