{"total":35,"rows":[{"id":"2504.20571","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","created":"2025-04-29","cited_by_count":295,"area":"lr"},{"id":"2504.16084","title":"TTRL: Test-Time Reinforcement Learning","created":"2025-04-22","cited_by_count":275,"area":"lr"},{"id":"2504.13818","title":"Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning","created":"2025-04-18","cited_by_count":84,"area":"lr"},{"id":"2506.08745","title":"Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning","created":"2025-06-10","cited_by_count":46,"area":"lr"},{"id":"2506.09340","title":"RePO: Replay-Enhanced Policy Optimization","created":"2025-06-11","cited_by_count":39,"area":"lr"},{"id":"2509.21268","title":"MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources","created":"2025-09-25","cited_by_count":39,"area":"lr"},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2507.22607","title":"VL-Cogito: Progressive Curriculum Reinforcement Learning for Advanced Multimodal Reasoning","created":"2025-07-30","cited_by_count":26,"area":"lr"},{"id":"2505.23363","title":"Discriminative Policy Optimization for Token-Level Reward Models","created":"2025-05-29","cited_by_count":16,"area":"lr"},{"id":"2505.02686","title":"Sailing by the Stars: A Survey on Reward Models and Learning Strategies for Learning from Rewards","created":"2025-05-05","cited_by_count":14,"area":"lr"},{"id":"2602.01970","title":"Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models","created":"2026-02-02","cited_by_count":14,"area":"lr"},{"id":"2504.13592","title":"Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling","created":"2025-04-18","cited_by_count":12,"area":"lr"},{"id":"2506.04695","title":"Reshaping Reasoning in LLMs: A Theoretical Analysis of RL Training Dynamics through Pattern Selection","created":"2025-06-05","cited_by_count":12,"area":"lr"},{"id":"2506.11480","title":"LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment","created":"2025-06-13","cited_by_count":9,"area":"lr"},{"id":"2505.18917","title":"Behavior Injection: Preparing Language Models for Reinforcement Learning","created":"2025-05-25","cited_by_count":8,"area":"lr"},{"id":"2506.18631","title":"ReDit: Reward Dithering for Improved LLM Policy Optimization","created":"2025-06-23","cited_by_count":8,"area":"lr"},{"id":"2510.01925","title":"Enhancing Large Language Model Reasoning with Reward Models: An Analytical Survey","created":"2025-10-02","cited_by_count":8,"area":"lr"},{"id":"2601.04809","title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2606.15576","title":"Localizing Credit at the Divergence: Path-Conditioned Self-Distillation for LLM Reasoning","created":"2026-06-14","cited_by_count":7,"area":"lr"},{"id":"2607.22002","title":"Learning as Reasoning Unfolds: Progressive Rollout Allocation for Efficient Reinforcement Learning","created":"2026-07-24","cited_by_count":7,"area":"lr"},{"id":"2601.07389","title":"On the Non-decoupling of Supervised Fine-tuning and Reinforcement Learning in Post-training","created":"2026-01-12","cited_by_count":6,"area":"lr"},{"id":"2511.07483","title":"Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning","created":"2025-11-09","cited_by_count":3,"area":"lr"},{"id":"2505.23247","title":"Accelerating RLHF Training with Reward Variance Increase","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2601.04670","title":"Learning Dynamics in RL Post-Training for Language Models","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"id":"2606.29296","title":"Process Advantage Signal Shaping: A Paradigm-Agnostic Middleware for Process-Supervised RL in LLM Reasoners","created":"2026-06-28","cited_by_count":2,"area":"lr"},{"id":"2509.22115","title":"Learning More with Less: A Dynamic Dual-Level Down-Sampling Framework for Efficient Policy Optimization","created":"2025-09-26","cited_by_count":1,"area":"lr"},{"id":"2605.00754","title":"Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring","created":"2026-05-01","cited_by_count":1,"area":"lr"},{"id":"2605.10158","title":"Unsupervised Process Reward Models","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2609.12459","title":"EvoRS: On-Policy Self-Evolution of Reward Systems for Open-Ended Reinforcement Learning","created":"2026-09-11","cited_by_count":1,"area":"lr"},{"id":"2605.10716","title":"What should post-training optimize? A test-time scaling law perspective","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2606.10931","title":"It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2609.32722","title":"Scaling Properties of Same-Family On-Policy Distillation","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2610.15778","title":"Who Sets the Pace of Judge Hacking? Judge Capability versus the Policy-Judge Gap","created":"2026-10-11","cited_by_count":0,"area":"lr"},{"id":"2610.17771","title":"Many Right Answers, One Training Example: Removing Responder Noise from GRPO for LLM Recommenders","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}