{"total":59,"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":"2508.05629","title":"On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification","created":"2025-08-07","cited_by_count":127,"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":"2506.19767","title":"SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning","created":"2025-06-24","cited_by_count":84,"area":"lr"},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2509.07430","title":"The Choice of Divergence: A Neglected Key to Mitigating Diversity Collapse in Reinforcement Learning with Verifiable Reward","created":"2025-09-09","cited_by_count":37,"area":null},{"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":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2510.00526","title":"Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum","created":"2025-10-01","cited_by_count":18,"area":null},{"id":"2508.16546","title":"RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs","created":"2025-08-22","cited_by_count":17,"area":null},{"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":"2512.13095","title":"ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2601.18984","title":"Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning","created":"2026-01-26","cited_by_count":11,"area":"lr"},{"id":"2604.23747","title":"SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning","created":"2026-04-26","cited_by_count":9,"area":"lr"},{"id":"2604.12627","title":"KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance","created":"2026-04-14","cited_by_count":8,"area":"lr"},{"id":"2602.14147","title":"LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models","created":"2026-02-15","cited_by_count":7,"area":"lr"},{"id":"2606.26027","title":"Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It","created":"2026-06-24","cited_by_count":7,"area":"agents"},{"id":"2601.19928","title":"Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures","created":"2026-01-11","cited_by_count":6,"area":"lr"},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2608.03972","title":"ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning","created":"2026-08-04","cited_by_count":6,"area":"lr"},{"id":"2508.06944","title":"AMFT: Aligning LLM Reasoners by Meta-Learning the Optimal Imitation-Exploration Balance","created":"2025-08-09","cited_by_count":5,"area":"lr"},{"id":"2606.18089","title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","created":"2026-06-16","cited_by_count":5,"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":"2511.07372","title":"Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training","created":"2025-11-10","cited_by_count":4,"area":"lr"},{"id":"2604.00513","title":"MOON3.0: Reasoning-aware Multimodal Representation Learning for E-commerce Product Understanding","created":"2026-04-01","cited_by_count":4,"area":"lr"},{"id":"2605.31228","title":"EchoRL: Reinforcement Learning via Rollout Echoing","created":"2026-05-29","cited_by_count":4,"area":"lr"},{"id":"2606.09932","title":"When RL Fails after SFT: Rejuvenating Model Plasticity for Robust SFT-to-RL Handoff","created":"2026-06-07","cited_by_count":4,"area":null},{"id":"2510.02227","title":"More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration","created":"2025-10-02","cited_by_count":3,"area":"lr"},{"id":"2510.26519","title":"Think Outside the Policy: In-Context Steered Policy Optimization","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2511.16602","title":"Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2511.21075","title":"Aligning LLMs with Biomedical Knowledge using Balanced Fine-Tuning","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2512.17636","title":"Trust-Region Adaptive Policy Optimization","created":"2025-12-19","cited_by_count":3,"area":"lr"},{"id":"2603.13985","title":"Supervised Fine-Tuning versus Reinforcement Learning: A Study of Post-Training Methods for Large Language Models","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2604.14932","title":"WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2605.22567","title":"LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance","created":"2026-05-21","cited_by_count":3,"area":"lr"},{"id":"2606.16215","title":"PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2510.12643","title":"Reasoning Pattern Matters: Learning to Reason without Human Rationales","created":"2025-10-14","cited_by_count":2,"area":"lr"},{"id":"2512.20760","title":"Generalization of RLVR Using Causal Reasoning as a Testbed","created":"2025-12-23","cited_by_count":2,"area":"lr"},{"id":"2601.09233","title":"GIFT: Reconciling Post-Training Objectives via Variational Finite-Temperature Gibbs Initialization","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2509.18600","title":"OraPO: Oracle-educated Reinforcement Learning for Data-efficient and Factual Radiology Report Generation","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2602.00400","title":"KEPO: Knowledge-Enhanced Preference Optimization for Multimodal Reasoning with Applications to Medical VQA","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2604.14258","title":"GFT: From Imitation to Reward Fine-Tuning with Unbiased Group Advantages and Dynamic Coefficient Rectification","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2605.05112","title":"Rollout Pass-Rate Control: Steering Binary-Reward RL Toward Its Most Informative Regime","created":"2026-05-06","cited_by_count":1,"area":"agents"},{"id":"2605.29303","title":"Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"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":"2607.28997","title":"Think2Go: Generative Next POI Recommendation with LLM Reasoning","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2602.10819","title":"RePO: Bridging On-Policy Learning and Off-Policy Knowledge through Rephrasing Policy Optimization","created":"2026-02-11","cited_by_count":0,"area":"alignment"},{"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":"2603.18088","title":"Enhancing Reinforcement Learning Fine-Tuning with an Online Refiner","created":"2026-03-18","cited_by_count":0,"area":"lr"},{"id":"2604.07747","title":"Mitigating Distribution Sharpening in Math RLVR via Distribution-Aligned Hint Synthesis and Backward Hint Annealing","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.15012","title":"Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2606.29706","title":"ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question Answering","created":"2026-06-29","cited_by_count":0,"area":"rag"},{"id":"2608.21811","title":"Hints, Critics, and Teachers: Prior Injection for Sparse-Reward RL in Vision-Language Math Reasoning","created":"2026-08-22","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":"2609.37898","title":"Guide, Then Let Go: Gap-Adaptive Teacher Scheduling for Sparse-Reward Agentic RL","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.02140","title":"Finetuning with Sampling: SFT Learns Better Than You Think","created":"2026-10-01","cited_by_count":0,"area":"deeprl"},{"id":"2610.12914","title":"OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models","created":"2026-10-09","cited_by_count":0,"area":"vla"}],"next_cursor":null}