{"total":146,"rows":[{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"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":"2505.19590","title":"Learning to Reason without External Rewards","created":"2025-05-26","cited_by_count":210,"area":"lr"},{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209,"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":"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":"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":"2511.16043","title":"Agent0: Unleashing Self-Evolving Agents from Zero Data via Tool-Integrated Reasoning","created":"2025-11-20","cited_by_count":75,"area":"lr"},{"id":"2505.21444","title":"Can Large Reasoning Models Self-Train?","created":"2025-05-27","cited_by_count":68,"area":"lr"},{"id":"2506.06395","title":"Confidence Is All You Need: Few-Shot RL Fine-Tuning of Language Models","created":"2025-06-05","cited_by_count":62,"area":"lr"},{"id":"2510.23595","title":"Multi-Agent Evolve: LLM Self-Improve through Co-evolution","created":"2025-10-27","cited_by_count":60,"area":"lr"},{"id":"2511.15661","title":"VisPlay: Self-Evolving Vision-Language Models from Images","created":"2025-11-19","cited_by_count":47,"area":"lr"},{"id":"2505.13308","title":"Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space","created":"2025-05-19","cited_by_count":43,"area":"lr"},{"id":"2505.13988","title":"The Hallucination Tax of Reinforcement Finetuning","created":"2025-05-20","cited_by_count":40,"area":"lr"},{"id":"2510.09285","title":"Spotlight on Token Perception for Multimodal Reinforcement Learning","created":"2025-10-10","cited_by_count":39,"area":"lr"},{"id":"2505.23590","title":"Jigsaw-R1: A Study of Rule-based Visual Reinforcement Learning with Jigsaw Puzzles","created":"2025-05-29","cited_by_count":36,"area":"lr"},{"id":"2507.23751","title":"CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks","created":"2025-07-31","cited_by_count":32,"area":"lr"},{"id":"2509.23863","title":"SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models","created":"2025-09-28","cited_by_count":29,"area":"lr"},{"id":"2602.10885","title":"Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics","created":"2026-02-11","cited_by_count":26,"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":"2505.07215","title":"Measuring General Intelligence with Generated Games","created":"2025-05-12","cited_by_count":24,"area":"lr"},{"id":"2508.00410","title":"Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models","created":"2025-08-01","cited_by_count":23,"area":"lr"},{"id":"2505.17989","title":"Outcome-based Reinforcement Learning to Predict the Future","created":"2025-05-23","cited_by_count":22,"area":"lr"},{"id":"2603.09206","title":"MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data","created":"2026-03-10","cited_by_count":21,"area":"lr"},{"id":"2509.03581","title":"Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents","created":"2025-09-03","cited_by_count":20,"area":"lr"},{"id":"2601.22628","title":"TTCS: Test-Time Curriculum Synthesis for Self-Evolving","created":"2026-01-30","cited_by_count":19,"area":"lr"},{"id":"2506.13351","title":"Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks","created":"2025-06-16","cited_by_count":18,"area":"lr"},{"id":"2608.06296","title":"On-Policy Self-Distillation without Any Supervision","created":"2026-08-06","cited_by_count":17,"area":"lr"},{"id":"2505.17063","title":"Synthetic Data RL: Task Definition Is All You Need","created":"2025-05-18","cited_by_count":15,"area":"lr"},{"id":"2506.00022","title":"Scaling Physical Reasoning with the PHYSICS Dataset","created":"2025-05-21","cited_by_count":13,"area":"lr"},{"id":"2601.18778","title":"Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability","created":"2026-01-26","cited_by_count":13,"area":"lr"},{"id":"2510.00911","title":"RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training","created":"2025-10-01","cited_by_count":12,"area":"lr"},{"id":"2602.03279","title":"Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2603.17775","title":"CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution","created":"2026-03-18","cited_by_count":12,"area":"lr"},{"id":"2603.19880","title":"What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time","created":"2026-03-20","cited_by_count":12,"area":"lr"},{"id":"2505.19439","title":"Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers","created":"2025-05-26","cited_by_count":11,"area":"lr"},{"id":"2508.21107","title":"Learning to Generate Unit Test via Adversarial Reinforcement Learning","created":"2025-08-28","cited_by_count":11,"area":"lr"},{"id":"2509.24193","title":"AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play","created":"2025-09-29","cited_by_count":10,"area":"lr"},{"id":"2512.24574","title":"Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time","created":"2025-12-31","cited_by_count":10,"area":"lr"},{"id":"2601.10094","title":"V-Zero: Self-Improving Multimodal Reasoning with Zero Annotation","created":"2026-01-15","cited_by_count":10,"area":"lr"},{"id":"2602.13103","title":"R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training","created":"2026-02-13","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":"2509.19894","title":"PromptCoT 2.0: Scaling Prompt Synthesis for Large Language Model Reasoning","created":"2025-09-24","cited_by_count":9,"area":"lr"},{"id":"2509.24771","title":"LatentEvolve: Self-Evolving Test-Time Scaling in Latent Space","created":"2025-09-29","cited_by_count":9,"area":"lr"},{"id":"2602.10560","title":"When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning","created":"2026-02-11","cited_by_count":9,"area":"lr"},{"id":"2505.17454","title":"Self-Training Large Language Models with Confident Reasoning","created":"2025-05-23","cited_by_count":8,"area":"lr"},{"id":"2508.16665","title":"Trust but Verify! A Survey on Verification Design for Test-time Scaling","created":"2025-08-20","cited_by_count":8,"area":"lr"},{"id":"2510.27072","title":"Towards Understanding Self-play for LLM Reasoning","created":"2025-10-31","cited_by_count":8,"area":"lr"},{"id":"2511.09907","title":"Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis","created":"2025-11-13","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":"2511.13612","title":"P1: Mastering Physics Olympiads with Reinforcement Learning","created":"2025-11-17","cited_by_count":8,"area":"lr"},{"id":"2601.04809","title":"SCALER:Synthetic Scalable Adaptive Learning Environment for Reasoning","created":"2026-01-08","cited_by_count":8,"area":"lr"},{"id":"2605.14392","title":"Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis","created":"2026-05-14","cited_by_count":8,"area":"lr"},{"id":"2511.00602","title":"OpenSIR: Open-Ended Self-Improving Reasoner","created":"2025-11-01","cited_by_count":7,"area":"lr"},{"id":"2604.01840","title":"Not All Tokens See Equally: Perception-Grounded Policy Optimization for Large Vision-Language Models","created":"2026-04-02","cited_by_count":7,"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":"2507.00951","title":"Thinking Beyond Tokens: From Brain-Inspired Intelligence to Cognitive Foundations for Artificial General Intelligence and its Societal Impact","created":"2025-07-01","cited_by_count":6,"area":"lr"},{"id":"2508.12338","title":"Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective Feedback","created":"2025-08-17","cited_by_count":6,"area":"lr"},{"id":"2508.17291","title":"Meta-R1: Empowering Large Reasoning Models with Metacognition","created":"2025-08-24","cited_by_count":6,"area":"lr"},{"id":"2510.02752","title":"The Path of Self-Evolving Large Language Models: Achieving Data-Efficient Learning via Intrinsic Feedback","created":"2025-10-03","cited_by_count":6,"area":"lr"},{"id":"2512.16917","title":"Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning","created":"2025-12-18","cited_by_count":6,"area":"lr"},{"id":"2601.13761","title":"DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution","created":"2026-01-20","cited_by_count":6,"area":"lr"},{"id":"2603.15255","title":"SAGE: Multi-Agent Self-Evolution for LLM Reasoning","created":"2026-03-16","cited_by_count":6,"area":"lr"},{"id":"2509.18083","title":"Reasoning Core: A Scalable RL Environment for LLM Symbolic Reasoning","created":"2025-09-22","cited_by_count":5,"area":"lr"},{"id":"2509.21549","title":"Correct Reasoning Paths Visit Shared Decision Pivots","created":"2025-09-25","cited_by_count":5,"area":"lr"},{"id":"2603.21289","title":"When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning","created":"2026-03-22","cited_by_count":5,"area":"lr"},{"id":"2604.14144","title":"SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments","created":"2026-04-15","cited_by_count":5,"area":"lr"},{"id":"2606.08708","title":"PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping","created":"2026-06-07","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":"2508.06412","title":"Sample-efficient LLM Optimization with Reset Replay","created":"2025-08-08","cited_by_count":4,"area":"lr"},{"id":"2511.00066","title":"Sharpness-Guided Group Relative Policy Optimization via Probability Shaping","created":"2025-10-29","cited_by_count":4,"area":"lr"},{"id":"2605.04984","title":"Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers","created":"2026-05-06","cited_by_count":4,"area":"lr"},{"id":"2605.22217","title":"Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL","created":"2026-05-21","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":"2507.18122","title":"Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical Reasoning","created":"2025-07-24","cited_by_count":3,"area":"lr"},{"id":"2509.21482","title":"Learning to Reason with Mixture of Tokens","created":"2025-09-25","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":"2606.18284","title":"Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier","created":"2026-06-10","cited_by_count":3,"area":"lr"},{"id":"2606.27721","title":"Learning to Reason with Curriculum II: Compositional Generalization","created":"2026-06-26","cited_by_count":3,"area":"lr"},{"id":"2607.20166","title":"Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning","created":"2026-07-22","cited_by_count":3,"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":"2602.03414","title":"Socratic-Geo: Synthetic Data Generation and Geometric Reasoning via Multi-Agent Interaction","created":"2026-02-03","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":"2603.02099","title":"Recursive Think-Answer Process for LLMs and VLMs","created":"2026-03-02","cited_by_count":2,"area":"lr"},{"id":"2603.13309","title":"Preventing Curriculum Collapse in Self-Evolving Reasoning Systems","created":"2026-03-03","cited_by_count":2,"area":"lr"},{"id":"2603.16223","title":"Dual Consensus: Escaping from Spurious Majority in Unsupervised RLVR via Two-Stage Vote Mechanism","created":"2026-03-17","cited_by_count":2,"area":"lr"},{"id":"2603.27375","title":"Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models","created":"2026-03-28","cited_by_count":2,"area":"lr"},{"id":"2605.16727","title":"PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play","created":"2026-05-16","cited_by_count":2,"area":"lr"},{"id":"2605.24794","title":"DUEL: Adversarial Self-Play for Multimodal Reasoning","created":"2026-05-24","cited_by_count":2,"area":"lr"},{"id":"2510.17868","title":"UniCode: Augmenting Evaluation for Code Reasoning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2511.19343","title":"Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning","created":"2025-11-24","cited_by_count":1,"area":"lr"},{"id":"2601.05633","title":"GIFT: Games as Informal Training for Generalizable LLMs","created":"2026-01-09","cited_by_count":1,"area":"lr"},{"id":"2602.03084","title":"AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2604.25419","title":"JURY-RL: Votes Propose, Proofs Dispose for Label-Free RLVR","created":"2026-04-28","cited_by_count":1,"area":"lr"},{"id":"2605.06638","title":"Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key","created":"2026-05-07","cited_by_count":1,"area":"lr"},{"id":"2605.07465","title":"SEIF: Self-Evolving Reinforcement Learning for Instruction Following","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.11006","title":"An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning","created":"2026-05-10","cited_by_count":1,"area":"lr"},{"id":"2605.11636","title":"Seir\\^enes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.20006","title":"GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable Rewards","created":"2026-05-19","cited_by_count":1,"area":"lr"}],"next_cursor":"100"}