{"total":61,"rows":[{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2511.08567","title":"The Path Not Taken: RLVR Provably Learns Off the Principals","created":"2025-11-11","cited_by_count":56,"area":"lr"},{"id":"2509.21128","title":"RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs","created":"2025-09-25","cited_by_count":34,"area":"lr"},{"id":"2604.13010","title":"Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation","created":"2026-04-14","cited_by_count":33,"area":"lr"},{"id":"2509.25666","title":"Nudging the Boundaries of LLM Reasoning","created":"2025-09-30","cited_by_count":26,"area":"lr"},{"id":"2510.00553","title":"On Predictability of Reinforcement Learning Dynamics for Large Language Models","created":"2025-10-01","cited_by_count":23,"area":"lr"},{"id":"2603.22446","title":"Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs","created":"2026-03-23","cited_by_count":20,"area":"lr"},{"id":"2608.06296","title":"On-Policy Self-Distillation without Any Supervision","created":"2026-08-06","cited_by_count":17,"area":"lr"},{"id":"2602.04118","title":"Learning to Reason in 13 Parameters","created":"2026-02-04","cited_by_count":14,"area":"lr"},{"id":"2509.19249","title":"Reinforcement Learning on Pre-Training Data","created":"2025-09-23","cited_by_count":12,"area":"lr"},{"id":"2602.01058","title":"Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2602.12566","title":"To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models","created":"2026-02-13","cited_by_count":11,"area":"lr"},{"id":"2601.23143","title":"THINKSAFE: Self-Generated Safety Alignment for Reasoning Models","created":"2026-01-30","cited_by_count":10,"area":"lr"},{"id":"2602.02244","title":"Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2602.22538","title":"RAIN-Merging: A Gradient-Free Method to Enhance Instruction Following in Large Reasoning Models with Preserved Thinking Format","created":"2026-02-26","cited_by_count":9,"area":"lr"},{"id":"2509.22637","title":"Variational Reasoning for Language Models","created":"2025-09-26","cited_by_count":8,"area":"lr"},{"id":"2510.00237","title":"Debunk the Myth of SFT Generalization","created":"2025-09-30","cited_by_count":8,"area":"lr"},{"id":"2510.27072","title":"Towards Understanding Self-play for LLM Reasoning","created":"2025-10-31","cited_by_count":8,"area":"lr"},{"id":"2603.01761","title":"Position: Modular Memory is the Key to Continual Learning Agents","created":"2026-03-02","cited_by_count":8,"area":"lr"},{"id":"2604.01499","title":"Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training","created":"2026-04-02","cited_by_count":8,"area":"lr"},{"id":"2604.14164","title":"How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2605.09725","title":"On-Policy Distillation with Best-of-N Teacher Rollout Selection","created":"2026-05-10","cited_by_count":7,"area":"lr"},{"id":"2510.10976","title":"Video-STR: Reinforcing MLLMs in Video Spatio-Temporal Reasoning with Relation Graph","created":"2025-10-13","cited_by_count":6,"area":"lr"},{"id":"2601.09269","title":"RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering","created":"2026-01-14","cited_by_count":6,"area":"lr"},{"id":"2603.25419","title":"TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning","created":"2026-03-26","cited_by_count":6,"area":"lr"},{"id":"2607.28449","title":"Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models","created":"2026-07-30","cited_by_count":5,"area":"lr"},{"id":"2604.04767","title":"Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2604.11805","title":"Solving Physics Olympiad via Reinforcement Learning on Physics Simulators","created":"2026-04-13","cited_by_count":4,"area":"lr"},{"id":"2605.05365","title":"ZAYA1-8B Technical Report","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2602.01103","title":"Probing RLVR training instability through the lens of objective-level hacking","created":"2026-02-01","cited_by_count":3,"area":"lr"},{"id":"2603.01683","title":"Surgical Post-Training: Proximal On-Policy Distillation for Reasoning with Knowledge Retention","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2605.21468","title":"You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories","created":"2026-05-20","cited_by_count":3,"area":"lr"},{"id":"2606.02398","title":"A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2512.01848","title":"Beyond SFT: Reinforcement Learning for Safer Large Reasoning Models with Better Reasoning Ability","created":"2025-12-01","cited_by_count":2,"area":"lr"},{"id":"2512.11470","title":"Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning","created":"2025-12-12","cited_by_count":2,"area":"lr"},{"id":"2512.13262","title":"Post-Training and Test-Time Scaling of Generative Agent Behavior Models for Interactive Autonomous Driving","created":"2025-12-15","cited_by_count":2,"area":"lr"},{"id":"2601.08274","title":"Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees","created":"2026-01-13","cited_by_count":2,"area":"lr"},{"id":"2605.06523","title":"On the Implicit Reward Overfitting and the Low-rank Dynamics in RLVR","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2606.09396","title":"PriFT: Prior-Support Guided Supervised Fine-Tuning","created":"2026-06-08","cited_by_count":2,"area":"lr"},{"id":"2606.22938","title":"Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently","created":"2026-06-22","cited_by_count":2,"area":"lr"},{"id":"2607.19331","title":"ISO: An RLVR-Native Optimization Stack","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2608.03573","title":"SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs","created":"2026-08-04","cited_by_count":2,"area":"lr"},{"id":"2604.03179","title":"Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models","created":"2026-04-03","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":"2606.05145","title":"Failed Reasoning Traces Tell You What Is Fixable (But Not by Reading Them)","created":"2026-06-03","cited_by_count":1,"area":"lr"},{"id":"2509.25455","title":"PIPer: On-Device Environment Setup via Online Reinforcement Learning","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2601.21192","title":"Do Reasoning Models Enhance Embedding Models?","created":"2026-01-29","cited_by_count":0,"area":"lr"},{"id":"2603.11321","title":"Hindsight-Anchored Policy Optimization: Learning Through Hindsight with Thompson Sampling-Inspired Adaptive Gating","created":"2026-03-11","cited_by_count":0,"area":"lr"},{"id":"2605.18903","title":"Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era","created":"2026-05-17","cited_by_count":0,"area":"lr"},{"id":"2605.26924","title":"Learning to Adapt SFT Data for Better Reasoning Generalization","created":"2026-05-26","cited_by_count":0,"area":"lr"},{"id":"2608.13698","title":"GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2608.18574","title":"Beyond Forgetting: Diagnosing and Harnessing Shared Reasoning in Continual RLVR","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.25936","title":"One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.25618","title":"Reasoning-Preserving Fine-Tuning of Post-RL LLMs with Null-Basis LoRA","created":"2026-09-22","cited_by_count":0,"area":"lr"},{"id":"2609.28570","title":"DEEPO: Dual-Entropy Enhanced Policy Optimization for Hallucination in MLLMs","created":"2026-09-23","cited_by_count":0,"area":"lr"},{"id":"2610.01800","title":"LineupRL: Verifiable Reinforcement Learning for Time Series Captioning via Caption-to-Series Identification","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.02015","title":"On Language Drift during RLVR Post-Training","created":"2026-10-01","cited_by_count":0,"area":"lr"},{"id":"2610.04158","title":"How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.14270","title":"The Thinking Leakage in Reinforcement Learning for LLMs","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.19687","title":"Function-Space Temporal Self-Distillation for Policy Optimization","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}