{"total":68,"rows":[{"id":"2504.20571","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","created":"2025-04-29","cited_by_count":295,"area":"lr"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111,"area":"lr"},{"id":"2505.12346","title":"SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization","created":"2025-05-18","cited_by_count":89,"area":"lr"},{"id":"2508.08221","title":"Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning","created":"2025-08-11","cited_by_count":56,"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":"2507.04632","title":"Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?","created":"2025-07-07","cited_by_count":52,"area":"lr"},{"id":"2505.21297","title":"rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset","created":"2025-05-27","cited_by_count":51,"area":"lr"},{"id":"2505.19641","title":"SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond","created":"2025-05-26","cited_by_count":50,"area":"lr"},{"id":"2507.07017","title":"First Return, Entropy-Eliciting Explore","created":"2025-07-09","cited_by_count":45,"area":"lr"},{"id":"2504.21233","title":"Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math","created":"2025-04-30","cited_by_count":44,"area":"lr"},{"id":"2505.23433","title":"Diversity-Aware Policy Optimization for Large Language Model Reasoning","created":"2025-05-29","cited_by_count":41,"area":"lr"},{"id":"2509.15207","title":"FlowRL: Matching Reward Distributions for LLM Reasoning","created":"2025-09-18","cited_by_count":40,"area":"lr"},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2509.24803","title":"TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Models","created":"2025-09-29","cited_by_count":27,"area":null},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2510.01833","title":"Plan Then Action:High-Level Planning Guidance Reinforcement Learning for LLM Reasoning","created":"2025-10-02","cited_by_count":19,"area":"lr"},{"id":"2508.11016","title":"CURE: Critical-Token-Guided Re-Concatenation for Entropy-Collapse Prevention","created":"2025-08-14","cited_by_count":18,"area":"lr"},{"id":"2505.12366","title":"DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization","created":"2025-05-18","cited_by_count":16,"area":"lr"},{"id":"2602.01970","title":"Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models","created":"2026-02-02","cited_by_count":14,"area":"lr"},{"id":"2507.08297","title":"KAT-V1: Kwai-AutoThink Technical Report","created":"2025-07-11","cited_by_count":12,"area":"lr"},{"id":"2510.24832","title":"Scheduling Your LLM Reinforcement Learning with Reasoning Trees","created":"2025-10-28","cited_by_count":12,"area":"lr"},{"id":"2506.18237","title":"AdapThink: Adaptive Thinking Preferences for Reasoning Language Model","created":"2025-06-23","cited_by_count":11,"area":"lr"},{"id":"2510.11620","title":"Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation","created":"2025-10-13","cited_by_count":11,"area":"lr"},{"id":"2510.25992","title":"Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning","created":"2025-10-29","cited_by_count":11,"area":"lr"},{"id":"2603.10887","title":"Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models","created":"2026-03-11","cited_by_count":11,"area":"lr"},{"id":"2506.14731","title":"Ring-lite: Scalable Reasoning via C3PO-Stabilized Reinforcement Learning for LLMs","created":"2025-06-17","cited_by_count":10,"area":"lr"},{"id":"2507.06573","title":"From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization","created":"2025-07-09","cited_by_count":10,"area":"lr"},{"id":"2603.25184","title":"Train at Moving Edge: Online-Verified Prompt Selection for Efficient RL Training of Large Reasoning Model","created":"2026-03-26","cited_by_count":10,"area":"lr"},{"id":"2606.11119","title":"TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning","created":"2026-06-09","cited_by_count":10,"area":"agents"},{"id":"2606.01281","title":"RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning","created":"2026-05-31","cited_by_count":9,"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":"2602.20722","title":"Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning","created":"2026-02-24","cited_by_count":8,"area":"lr"},{"id":"2505.15074","title":"DISCO Balances the Scales: Adaptive Domain- and Difficulty-Aware Reinforcement Learning on Imbalanced Data","created":"2025-05-21","cited_by_count":7,"area":"lr"},{"id":"2505.21908","title":"Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding","created":"2025-05-28","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":"2505.14403","title":"Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoning","created":"2025-05-20","cited_by_count":6,"area":"lr"},{"id":"2506.08672","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","created":"2025-06-10","cited_by_count":6,"area":"lr"},{"id":"2604.11741","title":"Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games","created":"2026-04-13","cited_by_count":6,"area":"lr"},{"id":"2507.17548","title":"CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning","created":"2025-07-23","cited_by_count":4,"area":"lr"},{"id":"2602.05630","title":"Rewards as Labels: Revisiting RLVR from a Classification Perspective","created":"2026-02-05","cited_by_count":4,"area":"lr"},{"id":"2602.14468","title":"LACONIC: Length-Aware Constrained Reinforcement Learning for LLM","created":"2026-02-16","cited_by_count":4,"area":null},{"id":"2507.09850","title":"The Challenge of Teaching Reasoning to LLMs Without RL or Distillation","created":"2025-07-14","cited_by_count":3,"area":"lr"},{"id":"2602.00815","title":"Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement","created":"2026-01-31","cited_by_count":3,"area":"lr"},{"id":"2506.13066","title":"FinLMM-R1: Enhancing Financial Reasoning in LMM through Scalable Data and Reward Design","created":"2025-06-16","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":"2511.06380","title":"What Makes Reasoning Invalid: Echo Reflection Mitigation for Large Language Models","created":"2025-11-09","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":"2602.03452","title":"Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional Pairing","created":"2026-02-03","cited_by_count":2,"area":"lr"},{"id":"2603.07777","title":"Breaking Training Bottlenecks: Effective and Stable Reinforcement Learning for Coding Models","created":"2026-03-08","cited_by_count":2,"area":"lr"},{"id":"2603.21440","title":"KG-Hopper: Empowering Compact Open LLMs with Knowledge Graph Reasoning via Reinforcement Learning","created":"2026-03-22","cited_by_count":2,"area":"lr"},{"id":"2606.06828","title":"AdaGRPO: A Capability-Aware Adaptive Enhancement for Flow-based GRPO","created":"2026-06-05","cited_by_count":2,"area":"lr"},{"id":"2607.26253","title":"Early Verdicts, Better Budgets: Sequential Adaptive Rollout Allocation for Compute-Efficient RLVR","created":"2026-07-28","cited_by_count":2,"area":null},{"id":"2601.22521","title":"One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2602.21608","title":"MixSarc: A Bangla-English Code-Mixed Corpus for Implicit Meaning Identification","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2603.07927","title":"SWE-Fuse: Empowering Software Agents via Issue-free Trajectory Learning and Entropy-aware RLVR Training","created":"2026-03-09","cited_by_count":1,"area":"agents"},{"id":"2605.07244","title":"Experience Sharing in Mutual Reinforcement Learning for Heterogeneous Language Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.20865","title":"Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards","created":"2026-05-20","cited_by_count":1,"area":"lr"},{"id":"2605.30832","title":"SLAT: Segment-Level Adaptive Trimming for Efficient CoT Reasoning","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2608.08009","title":"Evidence-Grounded Forensic Reasoning for Detecting and Grounding Multi-Modal Media Manipulation","created":"2026-08-08","cited_by_count":1,"area":"lr"},{"id":"2605.17295","title":"DISA: Offline Importance Sampling for Distribution-Matching LLM-RL","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.19750","title":"Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2607.26862","title":"ReCo: Reweighting GRPO Against Distributional Concentration","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.29252","title":"Dynamic Important Example Mining for Reinforcement Finetuning","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.03729","title":"Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.38805","title":"Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}