{"total":42,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","created":"2025-08-15","cited_by_count":91,"area":"lr"},{"id":"2510.10689","title":"OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs","created":"2025-10-12","cited_by_count":59,"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":"2510.10974","title":"Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning","created":"2025-10-13","cited_by_count":20,"area":"lr"},{"id":"2508.17784","title":"Proximal Supervised Fine-Tuning","created":"2025-08-25","cited_by_count":16,"area":"lr"},{"id":"2510.04454","title":"Mitigating Forgetting Between Supervised and Reinforcement Learning Yields Stronger Reasoners","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2509.24203","title":"Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends","created":"2025-09-29","cited_by_count":15,"area":"lr"},{"id":"2601.14249","title":"Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment","created":"2026-01-20","cited_by_count":13,"area":"lr"},{"id":"2511.17938","title":"SPINE: Token-Selective Test-Time Reinforcement Learning with Entropy-Band Regularization","created":"2025-11-22","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":"2510.01539","title":"Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code","created":"2025-10-02","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":"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":"2511.06221","title":"Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B","created":"2025-11-09","cited_by_count":8,"area":"lr"},{"id":"2509.25604","title":"RFG: Test-Time Scaling for Diffusion Large Language Model Reasoning with Reward-Free Guidance","created":"2025-09-29","cited_by_count":7,"area":"lr"},{"id":"2603.14389","title":"From $\\log \\pi$ to $\\pi$: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight","created":"2026-03-15","cited_by_count":6,"area":"lr"},{"id":"2510.15990","title":"Can GRPO Help LLMs Transcend Their Pretraining Origin?","created":"2025-10-14","cited_by_count":5,"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":"2511.09222","title":"Toward Honest Language Models for Deductive Reasoning","created":"2025-11-12","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":"2510.20519","title":"Metis-HOME: Hybrid Optimized Mixture-of-Experts for Multimodal Reasoning","created":"2025-10-23","cited_by_count":2,"area":"lr"},{"id":"2511.10254","title":"Facial-R1: Aligning Reasoning and Recognition for Facial Emotion Analysis","created":"2025-11-13","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":"2608.12764","title":"Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents","created":"2026-08-13","cited_by_count":2,"area":"lr"},{"id":"2512.22955","title":"Diversity or Precision? A Deep Dive into Next Token Prediction","created":"2025-12-28","cited_by_count":1,"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":"2604.08926","title":"Bridging SFT and RL: Dynamic Policy Optimization for Robust Reasoning","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2605.11505","title":"Selective Off-Policy Reference Tuning with Plan Guidance","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2606.24064","title":"Beyond Trajectory Imitation: Strategy-Guided Policy Optimization for LLM Reasoning","created":"2026-06-23","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":"2510.27462","title":"VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision","created":"2025-10-31","cited_by_count":0,"area":"lr"},{"id":"2606.07006","title":"RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning","created":"2026-06-05","cited_by_count":0,"area":"lr"},{"id":"2606.16152","title":"The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2606.23740","title":"Weight-Space Geometry of Offline Reasoning Training","created":"2026-06-21","cited_by_count":0,"area":"lr"},{"id":"2609.05539","title":"Dual-Latent Memory Routing for Vision-Language Reasoning","created":"2026-09-02","cited_by_count":0,"area":"lr"},{"id":"2609.09707","title":"Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reasoning","created":"2026-09-09","cited_by_count":0,"area":"lr"},{"id":"2609.31571","title":"Strategically Diverse Sampling for Self-Training","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.33463","title":"Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2610.08923","title":"AdaGuard: Enhancing Safety and Policy Compliance with Reasoning-Enabled LLM-As-A-Judge Guardrails","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.17607","title":"Facts Don't Speak Louder than Words: The Behavioral Essence of Long-CoT Distillation","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}