{"total":21,"rows":[{"id":"2506.19807","title":"KnowRL: Exploring Knowledgeable Reinforcement Learning for Factuality","created":"2025-06-24","cited_by_count":20,"area":"lr"},{"id":"2510.18924","title":"Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients","created":"2025-10-21","cited_by_count":13,"area":"lr"},{"id":"2508.03100","title":"AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video","created":"2025-08-05","cited_by_count":12,"area":"lr"},{"id":"2603.13134","title":"When Right Meets Wrong: Bilateral Context Conditioning with Reward-Confidence Correction for GRPO","created":"2026-03-13","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":"2602.20722","title":"Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning","created":"2026-02-24","cited_by_count":8,"area":"lr"},{"id":"2601.23135","title":"Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2510.04072","title":"Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning","created":"2025-10-05","cited_by_count":4,"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":"2601.05002","title":"On the Hidden Objective Biases of Group-based Reinforcement Learning","created":"2026-01-08","cited_by_count":3,"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":"2602.00453","title":"FedMOA: Federated GRPO for Personalized Reasoning LLMs under Heterogeneous Rewards","created":"2026-01-31","cited_by_count":2,"area":"lr"},{"id":"2602.04380","title":"Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning","created":"2026-02-04","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":"2601.21476","title":"Thinking Seeds: Leveraging Historical Diversity for Position-Aware RL in LLMs","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2602.03102","title":"Consensus Group Relative Policy Optimization for Text Generation","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2605.22537","title":"F-TIS: Harnessing Diverse Models in Collaborative GRPO","created":"2026-05-21","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":"2511.06023","title":"Multi-Reward GRPO Fine-Tuning for De-biasing Large Language Models: A Study Based on Chinese-Context Discrimination Data","created":"2025-11-08","cited_by_count":0,"area":"lr"},{"id":"2605.06755","title":"Gradient Extrapolation-Based Policy Optimization","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2608.26684","title":"Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs","created":"2026-08-27","cited_by_count":0,"area":"lr"}],"next_cursor":null}