{"total":19,"rows":[{"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":"2602.08354","title":"Does Your Reasoning Model Implicitly Know When to Stop Thinking?","created":"2026-02-09","cited_by_count":19,"area":"lr"},{"id":"2601.10201","title":"Future-KL Regularized GRPO: Process-Level Credit Assignment from $f$-Divergence Regularization","created":"2026-01-15","cited_by_count":12,"area":"lr"},{"id":"2602.03048","title":"CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs","created":"2026-02-03","cited_by_count":12,"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":"2603.21563","title":"Counterfactual Credit Policy Optimization for Multi-Agent Collaboration","created":"2026-03-23","cited_by_count":10,"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":"2603.23085","title":"When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models","created":"2026-03-24","cited_by_count":6,"area":"lr"},{"id":"2602.13407","title":"On-Policy Supervised Fine-Tuning for Efficient Reasoning","created":"2026-02-13","cited_by_count":4,"area":"lr"},{"id":"2603.21574","title":"Adaptive Robust Estimator for Multi-Agent Reinforcement Learning","created":"2026-03-23","cited_by_count":2,"area":"lr"},{"id":"2607.23364","title":"On the Impossibility of Unbiased and Length-Invariant Policy Optimization with Outcome Rewards","created":"2026-07-25","cited_by_count":2,"area":"lr"},{"id":"2602.04265","title":"Boosting LLM Reasoning via Human-Inspired Reward Shaping","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2605.18500","title":"Implicit Hierarchical GRPO: Decoupling Tool Invocation from Execution for Tool-Integrated Mathematical Reasoning","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"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":"2605.24331","title":"CurveRL: Principled Distribution-Aware Context Reweighting for LLM Reasoning","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2607.01490","title":"Don't Let Gains FADE: Breaking Down Policy Gradient Weights in RL","created":"2026-07-01","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":"2609.34990","title":"MaPP: A Unified Marginalized Posterior-Predictive Framework for Data-Efficient RLVR","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.17824","title":"Checking the Checkers: A Synthesis of Verifier Noise and Robustness in RLVR","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}