{"total":63,"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":"2602.02482","title":"Expanding the Capabilities of Reinforcement Learning via Text Feedback","created":"2026-02-02","cited_by_count":53,"area":"alignment"},{"id":"2510.19807","title":"Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning","created":"2025-10-22","cited_by_count":52,"area":"lr"},{"id":"2601.18779","title":"POPE: Learning to Reason on Hard Problems via Privileged On-Policy Exploration","created":"2026-01-26","cited_by_count":42,"area":"lr"},{"id":"2507.02841","title":"StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason","created":"2025-07-03","cited_by_count":39,"area":"lr"},{"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":"2601.18795","title":"Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes","created":"2026-01-26","cited_by_count":16,"area":"lr"},{"id":"2510.09388","title":"Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts","created":"2025-10-10","cited_by_count":14,"area":"lr"},{"id":"2601.14209","title":"InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning","created":"2026-01-20","cited_by_count":14,"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":"2512.13095","title":"ADHint: Adaptive Hints with Difficulty Priors for Reinforcement Learning","created":"2025-12-15","cited_by_count":12,"area":"lr"},{"id":"2603.01223","title":"Learn Hard Problems During RL with Reference Guided Fine-tuning","created":"2026-03-01","cited_by_count":12,"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":"2605.02913","title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","created":"2026-04-08","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":"2510.04140","title":"Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs","created":"2025-10-05","cited_by_count":7,"area":"lr"},{"id":"2607.19313","title":"Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information","created":"2026-07-21","cited_by_count":7,"area":"lr"},{"id":"2603.20508","title":"Measuring Weak-to-Strong Legibility of Reasoning Models","created":"2026-03-20","cited_by_count":5,"area":"lr"},{"id":"2605.15224","title":"ICRL: Learning to Internalize Self-Critique with Reinforcement Learning","created":"2026-05-13","cited_by_count":4,"area":"lr"},{"id":"2605.15726","title":"Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR","created":"2026-05-15","cited_by_count":4,"area":"lr"},{"id":"2508.16677","title":"Recall-Extend Dynamics: Enhancing Small Language Models through Controlled Exploration and Refined Offline Integration","created":"2025-08-21","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":"2601.20829","title":"Training Reasoning Models on Saturated Problems via Failure-Prefix Conditioning","created":"2026-01-28","cited_by_count":3,"area":"lr"},{"id":"2602.24110","title":"Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance","created":"2026-02-27","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":"2603.21877","title":"P^2O: Joint Policy and Prompt Optimization","created":"2026-03-23","cited_by_count":3,"area":"lr"},{"id":"2605.08873","title":"CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2606.14579","title":"VISTA: View-Consistent Self-Verified Training for GUI Grounding","created":"2026-06-12","cited_by_count":3,"area":"lr"},{"id":"2606.18216","title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","created":"2026-06-16","cited_by_count":3,"area":"lr"},{"id":"2601.05787","title":"From Off-Policy to On-Policy: Enhancing GUI Agents via Bi-level Expert-to-Policy Assimilation","created":"2026-01-09","cited_by_count":2,"area":"agents"},{"id":"2601.19404","title":"RPO:Reinforcement Fine-Tuning with Partial Reasoning Optimization","created":"2026-01-27","cited_by_count":2,"area":"lr"},{"id":"2605.30290","title":"Self-Trained Verification for Training- and Test-Time Self-Improvement","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2509.25148","title":"AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models","created":"2025-09-29","cited_by_count":1,"area":"alignment"},{"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":"2602.02405","title":"Making Expert Reasoning Learnable with Self-Distillation","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2602.16833","title":"VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2602.22225","title":"SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG","created":"2025-12-17","cited_by_count":1,"area":"rag"},{"id":"2605.00610","title":"Decouple before Integration: Test-time Synthesis of SFT and RLVR Task Vectors","created":"2026-05-01","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":"2607.16205","title":"It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2608.20611","title":"Difficulty-Aware Semantic-ID Optimization for Generative Recommendation","created":"2026-08-20","cited_by_count":1,"area":"lr"},{"id":"2609.33085","title":"The Model Knows Another Way: Strategy Switching for Effective RLVR Exploration","created":"2026-09-27","cited_by_count":1,"area":null},{"id":"2610.02781","title":"OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation","created":"2026-10-02","cited_by_count":1,"area":"distill"},{"id":"2512.18857","title":"CORE: Concept-Oriented Reinforcement for Bridging the Definition-Application Gap in Mathematical Reasoning","created":"2025-12-21","cited_by_count":0,"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":"2603.18953","title":"Context Bootstrapped Reinforcement Learning","created":"2026-03-19","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":"2605.04308","title":"Memory as a Markov Matrix: Sample Efficient Knowledge Expansion via Token-to-Dictionary Mapping","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.15604","title":"VSPO: Vector-Steered Policy Optimization for Behavioral Control","created":"2026-05-15","cited_by_count":0,"area":"mechinterp"},{"id":"2606.04095","title":"POLARIS: Guiding Small Models to Write Long Stories","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.25450","title":"The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.24199","title":"Reasoning to Regulate: Chain-of-Thought for Traffic Rule Understanding","created":"2026-07-27","cited_by_count":0,"area":"lr"},{"id":"2607.27787","title":"LoRA Scaffolded Policy Optimization (LSPO): A Sampling-Time Low-Rank Scaffold for Recovering Reinforcement-Learning Gradient on Zero-Reward Cliff Prompts","created":"2026-07-30","cited_by_count":0,"area":"lr"},{"id":"2608.29188","title":"Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.12419","title":"MInTRL: Off-policy Intervention can boost On-policy RL","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.13060","title":"CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models","created":"2026-09-11","cited_by_count":0,"area":"lr"},{"id":"2609.34975","title":"Teach to Learn: Hint Annealing for Self-improving LLM Reasoning","created":"2026-09-28","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":"2610.02846","title":"Understanding Enrichment in Reinforcement Learning","created":"2026-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2610.15888","title":"Variance-Optimal State Resampling for Reinforcement Learning with Verifiable Rewards","created":"2026-10-11","cited_by_count":0,"area":"lr"},{"id":"2610.18868","title":"Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.19349","title":"Where to Start, How to Move: Analyzing Curricula under GRPO for Long-Horizon LLM Agents","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}