{"total":131,"rows":[{"id":"2507.01006","title":"GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","created":"2025-07-01","cited_by_count":466,"area":"lr"},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"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":"2508.10751","title":"Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models","created":"2025-08-14","cited_by_count":138,"area":"lr"},{"id":"2506.20512","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","created":"2025-06-25","cited_by_count":113,"area":"lr"},{"id":"2506.24119","title":"SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning","created":"2025-06-30","cited_by_count":100,"area":"lr"},{"id":"2508.19652","title":"Self-Rewarding Vision-Language Model via Reasoning Decomposition","created":"2025-08-27","cited_by_count":97,"area":"lr"},{"id":"2510.14901","title":"Reasoning with Sampling: Your Base Model is Smarter Than You Think","created":"2025-10-16","cited_by_count":89,"area":"lr"},{"id":"2507.10532","title":"Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination","created":"2025-07-14","cited_by_count":82,"area":"lr"},{"id":"2603.11137","title":"Scaling Reasoning Efficiently via Relaxed On-Policy Distillation","created":"2026-03-11","cited_by_count":82,"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":"2507.07017","title":"First Return, Entropy-Eliciting Explore","created":"2025-07-09","cited_by_count":45,"area":"lr"},{"id":"2507.13266","title":"QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation","created":"2025-07-17","cited_by_count":44,"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":"2601.21590","title":"Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening","created":"2026-01-29","cited_by_count":31,"area":"lr"},{"id":"2512.16912","title":"Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward","created":"2025-12-18","cited_by_count":27,"area":"lr"},{"id":"2509.25666","title":"Nudging the Boundaries of LLM Reasoning","created":"2025-09-30","cited_by_count":26,"area":"lr"},{"id":"2511.16660","title":"Cognitive Foundations for Reasoning and Their Manifestation in LLMs","created":"2025-11-20","cited_by_count":26,"area":"lr"},{"id":"2603.19835","title":"FIPO: Eliciting Deep Reasoning with Future-KL Influenced Policy Optimization","created":"2026-03-20","cited_by_count":25,"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":"2510.02230","title":"The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models","created":"2025-10-02","cited_by_count":18,"area":"lr"},{"id":"2507.11662","title":"Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification","created":"2025-07-15","cited_by_count":14,"area":"lr"},{"id":"2601.11061","title":"Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs","created":"2026-01-16","cited_by_count":14,"area":"lr"},{"id":"2507.00417","title":"ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context","created":"2025-07-01","cited_by_count":13,"area":"lr"},{"id":"2509.26114","title":"Clip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models","created":"2025-09-30","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":"2507.15337","title":"Reasoning Models are Test Exploiters: Rethinking Multiple-Choice","created":"2025-07-21","cited_by_count":11,"area":"lr"},{"id":"2509.07604","title":"K2-Think: A Parameter-Efficient Reasoning System","created":"2025-09-09","cited_by_count":11,"area":"lr"},{"id":"2512.22255","title":"Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks","created":"2025-12-24","cited_by_count":11,"area":"lr"},{"id":"2603.11682","title":"Entropy-Preserving Reinforcement Learning","created":"2026-03-12","cited_by_count":11,"area":"lr"},{"id":"2510.04230","title":"Pushing on Multilingual Reasoning Models with Language-Mixed Chain-of-Thought","created":"2025-10-05","cited_by_count":10,"area":"lr"},{"id":"2510.05251","title":"Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement Learning","created":"2025-10-06","cited_by_count":10,"area":"lr"},{"id":"2510.11653","title":"MATH-Beyond: A Benchmark for RL to Expand Beyond the Base Model","created":"2025-10-13","cited_by_count":10,"area":"lr"},{"id":"2511.23269","title":"OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoning","created":"2025-11-28","cited_by_count":10,"area":"lr"},{"id":"2507.00726","title":"Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess","created":"2025-07-01","cited_by_count":9,"area":"lr"},{"id":"2510.01459","title":"LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoning","created":"2025-10-01","cited_by_count":9,"area":"lr"},{"id":"2510.07312","title":"h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning","created":"2025-10-08","cited_by_count":9,"area":"lr"},{"id":"2603.02203","title":"Tool Verification for Test-Time Reinforcement Learning","created":"2026-03-02","cited_by_count":9,"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":"2506.18631","title":"ReDit: Reward Dithering for Improved LLM Policy Optimization","created":"2025-06-23","cited_by_count":8,"area":"lr"},{"id":"2507.12885","title":"VAR-MATH: Probing True Mathematical Reasoning in LLMS via Symbolic Multi-Instance Benchmarks","created":"2025-07-17","cited_by_count":8,"area":"lr"},{"id":"2509.06608","title":"Small Vectors, Big Effects: A Mechanistic Study of RL-Induced Reasoning via Steering Vectors","created":"2025-09-08","cited_by_count":8,"area":"lr"},{"id":"2510.03632","title":"MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information","created":"2025-10-04","cited_by_count":8,"area":"lr"},{"id":"2511.11881","title":"Better LLM Reasoning via Dual-Play","created":"2025-11-14","cited_by_count":8,"area":"lr"},{"id":"2601.07226","title":"Lost in the Noise: How Reasoning Models Fail with Contextual Distractors","created":"2026-01-12","cited_by_count":8,"area":"lr"},{"id":"2601.15279","title":"MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs","created":"2026-01-21","cited_by_count":8,"area":"lr"},{"id":"2603.21177","title":"Prompt replay: speeding up grpo with on-policy reuse of high-signal prompts","created":"2026-03-22","cited_by_count":8,"area":"lr"},{"id":"2509.21871","title":"Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization","created":"2025-09-26","cited_by_count":7,"area":"lr"},{"id":"2510.00177","title":"PrefDisco: Benchmarking Proactive Personalized Reasoning","created":"2025-09-30","cited_by_count":7,"area":"lr"},{"id":"2511.04800","title":"Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models","created":"2025-11-06","cited_by_count":7,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2508.05928","title":"Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting","created":"2025-08-08","cited_by_count":6,"area":"lr"},{"id":"2510.05132","title":"Training Large Language Models To Reason In Parallel With Global Forking Tokens","created":"2025-10-01","cited_by_count":6,"area":"lr"},{"id":"2510.27044","title":"Limits of Generalization in RLVR: Two Case Studies in Mathematical Reasoning","created":"2025-10-30","cited_by_count":6,"area":"lr"},{"id":"2601.18722","title":"Gained in Translation: Privileged Pairwise Judges Enhance Multilingual Reasoning","created":"2026-01-26","cited_by_count":6,"area":"lr"},{"id":"2602.16742","title":"DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning","created":"2026-02-18","cited_by_count":6,"area":"lr"},{"id":"2603.02091","title":"Learning from Synthetic Data Improves Multi-hop Reasoning","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2605.00380","title":"ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning","created":"2026-05-01","cited_by_count":6,"area":"lr"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","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":"2511.04694","title":"Reasoning Up the Instruction Ladder for Controllable Language Models","created":"2025-10-30","cited_by_count":5,"area":"lr"},{"id":"2605.04542","title":"Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation","created":"2026-05-06","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":"2607.13643","title":"Consensus as Privileged Context for Label-Free Self-Distillation","created":"2026-07-15","cited_by_count":5,"area":"lr"},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2509.04027","title":"Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought","created":"2025-09-04","cited_by_count":4,"area":"lr"},{"id":"2512.14944","title":"PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs","created":"2025-12-16","cited_by_count":4,"area":"lr"},{"id":"2602.11128","title":"Asymmetric Prompt Weighting for Reinforcement Learning with Verifiable Rewards","created":"2026-02-11","cited_by_count":4,"area":"lr"},{"id":"2602.14225","title":"Text Before Vision: Staged Knowledge Injection Matters for Agentic RLVR in Ultra-High-Resolution Remote Sensing Understanding","created":"2026-02-15","cited_by_count":4,"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":"2606.01075","title":"On the Generalization Gap in Self-Evolving Language Model Reasoning","created":"2026-05-31","cited_by_count":4,"area":"lr"},{"id":"2510.07761","title":"Test-Time Reasoners Are Strategic Multiple-Choice Test-Takers","created":"2025-10-09","cited_by_count":3,"area":"lr"},{"id":"2510.08977","title":"Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL","created":"2025-10-10","cited_by_count":3,"area":"lr"},{"id":"2510.17139","title":"Rethinking On-policy Optimization for Query Augmentation","created":"2025-10-20","cited_by_count":3,"area":"lr"},{"id":"2601.00215","title":"Disentangling Perception and Reasoning in Multimodal LLMs via Reward Design","created":"2026-01-01","cited_by_count":3,"area":"lr"},{"id":"2605.30327","title":"Reasoning with Sampling: Cutting at Decision Points","created":"2026-05-28","cited_by_count":3,"area":"lr"},{"id":"2507.11408","title":"KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning?","created":"2025-07-15","cited_by_count":2,"area":"lr"},{"id":"2507.17442","title":"Confident RAG: Enhancing the Performance of LLMs for Mathematics Question Answering through Multi-Embedding and Confidence Scoring","created":"2025-07-23","cited_by_count":2,"area":"lr"},{"id":"2510.07790","title":"GCPO: When Contrast Fails, Go Gold","created":"2025-10-09","cited_by_count":2,"area":"lr"},{"id":"2510.18814","title":"A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning","created":"2025-10-21","cited_by_count":2,"area":"lr"},{"id":"2512.03244","title":"ScalePRM: Training Process Reward Models by Scaling Verification Compute Without Ground Truth","created":"2025-12-02","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":"2602.20132","title":"LAD: Learning Advantage Distribution for Reasoning","created":"2026-02-23","cited_by_count":2,"area":"lr"},{"id":"2604.18574","title":"When Can LLMs Learn to Reason with Weak Supervision?","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2606.29971","title":"NeuReasoner: Theory-grounded Mapping of Reasoning Elicitation Boundaries","created":"2026-06-29","cited_by_count":2,"area":"lr"},{"id":"2608.17423","title":"Prism-GRPO: Faster VLA Policy Optimization via Splitting Same-outcome Groups","created":"2026-08-18","cited_by_count":2,"area":"lr"},{"id":"2601.04996","title":"AlgBench: To What Extent Do Large Reasoning Models Understand Algorithms?","created":"2026-01-08","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":"2602.03102","title":"Consensus Group Relative Policy Optimization for Text Generation","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2603.12826","title":"Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design","created":"2026-03-13","cited_by_count":1,"area":"lr"},{"id":"2605.20066","title":"Text-to-SPARQL Generation with Reinforcement Learning: A GRPO-based Approach on DBLP","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"id":"2606.06475","title":"RREDCoT: Segment-Level Reward Redistribution for Reasoning Models","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2607.09693","title":"Depth-Entropy Guided Sampling for Training-Free LLM Reasoning","created":"2026-06-19","cited_by_count":1,"area":"lr"},{"id":"2507.00054","title":"Enhancing Reasoning Capabilities in SLMs with Reward Guided Dataset Distillation","created":"2025-06-25","cited_by_count":0,"area":"lr"},{"id":"2509.24207","title":"Humanline: Online Alignment as Perceptual Loss","created":"2025-09-29","cited_by_count":0,"area":"lr"},{"id":"2510.01832","title":"SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning","created":"2025-10-02","cited_by_count":0,"area":"lr"},{"id":"2510.18619","title":"Visual Attention Reasoning via Hierarchical Search and Self-Verification","created":"2025-10-21","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}