{"total":106,"rows":[{"id":"2601.18734","title":"Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models","created":"2026-01-26","cited_by_count":455,"area":"lr"},{"id":"2601.19897","title":"Self-Distillation Enables Continual Learning","created":"2026-01-27","cited_by_count":247,"area":"offlinerl"},{"id":"2508.05004","title":"R-Zero: Self-Evolving Reasoning LLM from Zero Data","created":"2025-08-07","cited_by_count":228,"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":"2509.04259","title":"RL's Razor: Why Online Reinforcement Learning Forgets Less","created":"2025-09-04","cited_by_count":176,"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":"2512.07783","title":"On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models","created":"2025-12-08","cited_by_count":69,"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":"2507.07017","title":"First Return, Entropy-Eliciting Explore","created":"2025-07-09","cited_by_count":45,"area":"lr"},{"id":"2511.16334","title":"OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe","created":"2025-11-20","cited_by_count":37,"area":"lr"},{"id":"2510.03264","title":"Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data","created":"2025-09-26","cited_by_count":27,"area":"lr"},{"id":"2507.03112","title":"RLVER: Reinforcement Learning with Verifiable Emotion Rewards for Empathetic Agents","created":"2025-07-03","cited_by_count":25,"area":"lr"},{"id":"2509.20758","title":"SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs","created":"2025-09-25","cited_by_count":24,"area":null},{"id":"2509.21016","title":"RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?","created":"2025-09-25","cited_by_count":23,"area":null},{"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":"2508.17784","title":"Proximal Supervised Fine-Tuning","created":"2025-08-25","cited_by_count":16,"area":"lr"},{"id":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"id":"2604.06628","title":"Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability","created":"2026-04-08","cited_by_count":14,"area":"lr"},{"id":"2603.22117","title":"On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation","created":"2026-03-23","cited_by_count":13,"area":"lr"},{"id":"2507.05195","title":"Train-before-Test Harmonizes Language Model Rankings","created":"2025-07-07","cited_by_count":12,"area":null},{"id":"2510.20956","title":"Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training","created":"2025-10-23","cited_by_count":12,"area":"lr"},{"id":"2508.09883","title":"Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning","created":"2025-08-13","cited_by_count":11,"area":"lr"},{"id":"2507.14447","title":"Routine: A Structural Planning Framework for LLM Agent System in Enterprise","created":"2025-07-19","cited_by_count":9,"area":"agents"},{"id":"2510.14943","title":"LaSeR: Reinforcement Learning with Last-Token Self-Rewarding","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2508.20697","title":"Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning","created":"2025-08-28","cited_by_count":8,"area":null},{"id":"2509.23657","title":"Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2509.26313","title":"One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient","created":"2025-09-30","cited_by_count":8,"area":null},{"id":"2510.00237","title":"Debunk the Myth of SFT Generalization","created":"2025-09-30","cited_by_count":8,"area":"lr"},{"id":"2510.01032","title":"Meaningless Tokens, Meaningful Gains: How Activation Shifts Enhance LLM Reasoning","created":"2025-10-01","cited_by_count":8,"area":"lr"},{"id":"2512.24063","title":"How and Why LLMs Generalize: A Fine-Grained Analysis of LLM Reasoning from Cognitive Behaviors to Low-Level Patterns","created":"2025-12-30","cited_by_count":8,"area":"lr"},{"id":"2602.00173","title":"Learning Robust Reasoning through Guided Adversarial Self-Play","created":"2026-01-30","cited_by_count":8,"area":"lr"},{"id":"2510.11184","title":"Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalization","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2510.22543","title":"FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning","created":"2025-10-26","cited_by_count":7,"area":"lr"},{"id":"2606.01476","title":"OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification","created":"2026-05-31","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":"2601.09269","title":"RISER: Orchestrating Latent Reasoning Skills for Adaptive Activation Steering","created":"2026-01-14","cited_by_count":6,"area":"lr"},{"id":"2601.18217","title":"Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents","created":"2026-01-26","cited_by_count":6,"area":"agents"},{"id":"2509.21549","title":"Correct Reasoning Paths Visit Shared Decision Pivots","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2510.25528","title":"Zero Reinforcement Learning Towards General Domains","created":"2025-10-29","cited_by_count":5,"area":"lr"},{"id":"2512.12690","title":"Reassessing the Role of Supervised Fine-Tuning: An Empirical Study in VLM Reasoning","created":"2025-12-14","cited_by_count":5,"area":"lr"},{"id":"2512.23592","title":"Same or Not? Enhancing Visual Perception in Vision-Language Models","created":"2025-12-29","cited_by_count":5,"area":"mllm"},{"id":"2601.04992","title":"Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization","created":"2026-01-08","cited_by_count":5,"area":"lr"},{"id":"2601.21484","title":"ETS: Energy-Guided Test-Time Scaling for Training-Free RL Alignment","created":"2026-01-29","cited_by_count":5,"area":"lr"},{"id":"2602.17684","title":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models","created":"2026-02-04","cited_by_count":5,"area":"alignment"},{"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":"2606.25178","title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2508.06412","title":"Sample-efficient LLM Optimization with Reset Replay","created":"2025-08-08","cited_by_count":4,"area":"lr"},{"id":"2510.02272","title":"Parallel Scaling Law: Unveiling Reasoning Generalization through A Cross-Linguistic Perspective","created":"2025-10-02","cited_by_count":4,"area":"lr"},{"id":"2511.02463","title":"Extending RLVR to Open-Ended Tasks via Verifiable Multiple-Choice Reformulation","created":"2025-11-04","cited_by_count":4,"area":"lr"},{"id":"2511.05933","title":"Reinforcement Learning Improves Traversal of Parametric Knowledge in LLMs","created":"2025-11-08","cited_by_count":4,"area":null},{"id":"2602.03978","title":"Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning","created":"2026-02-03","cited_by_count":4,"area":"lr"},{"id":"2603.12011","title":"Can RL Improve Generalization of LLM Agents? An Empirical Study","created":"2026-03-12","cited_by_count":4,"area":"agents"},{"id":"2508.19988","title":"AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2511.00536","title":"Word Salad Chopper: Reasoning Models Waste A Ton Of Decoding Budget On Useless Repetitions, Self-Knowingly","created":"2025-11-01","cited_by_count":3,"area":"lr"},{"id":"2511.18787","title":"Understanding Task Transfer in Vision-Language Models","created":"2025-11-24","cited_by_count":3,"area":"mllm"},{"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":"2603.08371","title":"Leaderboard Incentives: Model Rankings under Strategic Post-Training","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2603.11193","title":"DeReason: A Difficulty-Aware Curriculum Improves Decoupled SFT-then-RL Training for General Reasoning","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"id":"2604.03004","title":"R2-Write: Reflection and Revision for Open-Ended Writing with Deep Reasoning","created":"2026-04-03","cited_by_count":3,"area":"lr"},{"id":"2604.25011","title":"Why Does Reinforcement Learning Generalize? A Feature-Level Mechanistic Study of Post-Training in Large Language Models","created":"2026-04-27","cited_by_count":3,"area":"lr"},{"id":"2605.10973","title":"Rotation-Preserving Supervised Fine-Tuning","created":"2026-05-08","cited_by_count":3,"area":null},{"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":"2606.18216","title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","created":"2026-06-16","cited_by_count":3,"area":"lr"},{"id":"2606.25013","title":"Do Thinking Tokens Help with Safety?","created":"2026-06-23","cited_by_count":3,"area":"lr"},{"id":"2606.31575","title":"Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index","created":"2026-06-30","cited_by_count":3,"area":"lr"},{"id":"2508.11386","title":"Retrieval-augmented reasoning with lean language models","created":"2025-08-15","cited_by_count":2,"area":"lr"},{"id":"2509.20321","title":"Conversational Speech Reveals Structural Robustness Failures in SpeechLLM Backbones","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2511.09865","title":"In-Token Rationality Optimization: Towards Accurate and Concise LLM Reasoning via Self-Feedback","created":"2025-11-13","cited_by_count":2,"area":"lr"},{"id":"2511.16885","title":"Improving Latent Reasoning in LLMs via Soft Concept Mixing","created":"2025-11-21","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":"2601.03111","title":"One Sample to Rule Them All: Extreme Data Efficiency in Multidiscipline Reasoning with Reinforcement Learning","created":"2026-01-06","cited_by_count":2,"area":"lr"},{"id":"2602.00085","title":"CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models","created":"2026-01-22","cited_by_count":2,"area":"lr"},{"id":"2603.02908","title":"SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training","created":"2026-03-03","cited_by_count":2,"area":"mechinterp"},{"id":"2605.28008","title":"Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2606.07812","title":"Scaling Participation in Modular AI Systems","created":"2026-06-05","cited_by_count":2,"area":null},{"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":"2508.10019","title":"Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2508.10409","title":"Dataset Construction for Training LLM to Learn Analog Circuit Knowledge","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2603.20799","title":"RLVR Training of LLMs Does Not Improve Thinking Ability for General QA: Evaluation Method and a Simple Solution","created":"2026-03-21","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":"2605.09879","title":"M2A: Synergizing Mathematical and Agentic Reasoning in Large Language Models","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2605.21467","title":"DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2510.10201","title":"RLFR: Extending Reinforcement Learning for LLMs with Flow Environment","created":"2025-10-11","cited_by_count":0,"area":"lr"},{"id":"2511.06776","title":"Data Trajectory Alignment for LLM Domain Adaptation: A Two-Phase Synthesis Framework for Telecommunications Mathematics","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2601.17467","title":"Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping","created":"2026-01-24","cited_by_count":0,"area":"lr"},{"id":"2603.03005","title":"OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured Agents","created":"2026-03-03","cited_by_count":0,"area":"lr"},{"id":"2603.16867","title":"Efficient Reasoning on the Edge","created":"2026-03-17","cited_by_count":0,"area":"lr"},{"id":"2604.08477","title":"SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2604.18639","title":"Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning","created":"2026-04-19","cited_by_count":0,"area":"synth"},{"id":"2605.25381","title":"Not only where, But when: Temporal Scheduling for RLVR","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.29190","title":"When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math Transfer","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"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":"2608.04761","title":"InsightEmb: Learning Action-Intent Embeddings for Agentic Insight Retrieval","created":"2026-08-05","cited_by_count":0,"area":"agents"},{"id":"2608.07786","title":"Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.16639","title":"ReDraft, Don't Just Distill: Reference-Driven Revision for Continual VLLM Post-Training","created":"2026-09-15","cited_by_count":0,"area":"mllm"},{"id":"2609.22146","title":"GRRR: The Geometry of Reshaping, Rotation, and Routing in Decoder LLM post-training","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.29230","title":"EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewards","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.35699","title":"Distillation Defenses Easily Break After Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.36952","title":"ER-JEPA: Experience Replay Improves Joint-Embedding Predictive Learning in Language Models","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38879","title":"Does Learning Protein Folding Generalize to Broader Reasoning?","created":"2026-09-30","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}