{"total":14,"rows":[{"id":"2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","created":"2026-04-02","cited_by_count":76,"area":"lr"},{"id":"2608.06243","title":"DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models","created":"2026-08-06","cited_by_count":7,"area":"lr"},{"id":"2601.06801","title":"Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2605.05965","title":"Beyond Uniform Credit Assignment: Selective Eligibility Traces for RLVR","created":"2026-05-07","cited_by_count":5,"area":"lr"},{"id":"2601.09260","title":"Efficient Paths and Dense Rewards: Probabilistic Flow Reasoning for Large Language Models","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2606.31825","title":"Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning","created":"2026-06-30","cited_by_count":2,"area":"lr"},{"id":"2608.20256","title":"Learning When to Think: Adaptive Reasoning for Test-Time Compute Allocation","created":"2026-08-20","cited_by_count":2,"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":"2607.07976","title":"When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2607.27888","title":"Not All Tokens Deserve Equal Credit: Counterfactual Sensitivity Credit Reallocation for Long-CoT Reasoning","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2609.27035","title":"Reinforcement Learning with Decomposed Subtasks","created":"2026-09-22","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"},{"id":"2610.09804","title":"BoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token Aggregation","created":"2026-10-07","cited_by_count":0,"area":"lr"}],"next_cursor":null}