{"total":914,"rows":[{"id":"2503.14476","title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale","created":"2025-03-18","cited_by_count":2810,"area":"lr"},{"id":"2504.13837","title":"Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?","created":"2025-04-18","cited_by_count":982,"area":"lr"},{"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":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513,"area":"lr"},{"id":"2503.18892","title":"SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild","created":"2025-03-24","cited_by_count":511,"area":"lr"},{"id":"2502.01456","title":"Process Reinforcement through Implicit Rewards","created":"2025-02-03","cited_by_count":504,"area":"lr"},{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497,"area":"lr"},{"id":"2505.22617","title":"The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models","created":"2025-05-28","cited_by_count":485,"area":"lr"},{"id":"2503.21776","title":"Video-R1: Reinforcing Video Reasoning in MLLMs","created":"2025-03-27","cited_by_count":484,"area":"lr"},{"id":"2503.16419","title":"Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models","created":"2025-03-20","cited_by_count":464,"area":"lr"},{"id":"2503.24290","title":"Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model","created":"2025-03-31","cited_by_count":461,"area":"lr"},{"id":"2505.14362","title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","created":"2025-05-20","cited_by_count":410,"area":"lr"},{"id":"2504.07491","title":"Kimi-VL Technical Report","created":"2025-04-10","cited_by_count":388,"area":"lr"},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384,"area":"lr"},{"id":"2503.05592","title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","created":"2025-03-07","cited_by_count":336,"area":"lr"},{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"area":"lr"},{"id":"2504.08837","title":"VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning","created":"2025-04-10","cited_by_count":323,"area":"lr"},{"id":"2502.17419","title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","created":"2025-02-24","cited_by_count":320,"area":"lr"},{"id":"2503.12937","title":"R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization","created":"2025-03-17","cited_by_count":301,"area":"lr"},{"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":"2504.03160","title":"DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments","created":"2025-04-04","cited_by_count":286,"area":"lr"},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281,"area":"lr"},{"id":"2504.11456","title":"DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning","created":"2025-04-15","cited_by_count":280,"area":"lr"},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263,"area":"lr"},{"id":"2504.06958","title":"VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning","created":"2025-04-09","cited_by_count":255,"area":"lr"},{"id":"2503.07536","title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","created":"2025-03-10","cited_by_count":248,"area":"lr"},{"id":"2507.02259","title":"MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent","created":"2025-07-03","cited_by_count":246,"area":"lr"},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2504.15895","title":"Dynamic Early Exit in Reasoning Models","created":"2025-04-22","cited_by_count":219,"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":"2508.15260","title":"Deep Think with Confidence","created":"2025-08-21","cited_by_count":205,"area":"lr"},{"id":"2601.05242","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","created":"2026-01-08","cited_by_count":193,"area":"lr"},{"id":"2504.01296","title":"ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning","created":"2025-04-02","cited_by_count":192,"area":"lr"},{"id":"2504.12216","title":"d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning","created":"2025-04-16","cited_by_count":186,"area":"lr"},{"id":"2503.12605","title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","created":"2025-03-16","cited_by_count":182,"area":"lr"},{"id":"2504.11354","title":"Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learning","created":"2025-04-15","cited_by_count":180,"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":"2503.10460","title":"Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond","created":"2025-03-13","cited_by_count":175,"area":"lr"},{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172,"area":"lr"},{"id":"2505.22312","title":"Skywork Open Reasoner 1 Technical Report","created":"2025-05-28","cited_by_count":165,"area":"lr"},{"id":"2501.18585","title":"Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs","created":"2025-01-30","cited_by_count":163,"area":"lr"},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2503.19470","title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","created":"2025-03-25","cited_by_count":161,"area":"lr"},{"id":"2504.01805","title":"SpaceR: Reinforcing MLLMs in Video Spatial Reasoning","created":"2025-04-02","cited_by_count":159,"area":"lr"},{"id":"2503.04472","title":"DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models","created":"2025-03-06","cited_by_count":158,"area":"lr"},{"id":"2503.23829","title":"Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains","created":"2025-03-31","cited_by_count":156,"area":"lr"},{"id":"2504.21318","title":"Phi-4-reasoning Technical Report","created":"2025-04-30","cited_by_count":151,"area":"lr"},{"id":"2505.13417","title":"AdaptThink: Reasoning Models Can Learn When to Think","created":"2025-05-19","cited_by_count":147,"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":"2502.06703","title":"Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling","created":"2025-02-10","cited_by_count":136,"area":"lr"},{"id":"2502.12025","title":"SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities","created":"2025-02-17","cited_by_count":136,"area":"lr"},{"id":"2502.21321","title":"LLM Post-Training: A Deep Dive into Reasoning Large Language Models","created":"2025-02-28","cited_by_count":135,"area":"lr"},{"id":"2503.21614","title":"A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond","created":"2025-03-27","cited_by_count":132,"area":"lr"},{"id":"2504.07912","title":"Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining","created":"2025-04-10","cited_by_count":129,"area":"lr"},{"id":"2502.09621","title":"MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency","created":"2025-02-13","cited_by_count":125,"area":"lr"},{"id":"2503.00555","title":"Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable","created":"2025-03-01","cited_by_count":122,"area":"lr"},{"id":"2505.07608","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","created":"2025-05-12","cited_by_count":121,"area":"lr"},{"id":"2504.07954","title":"Perception-R1: Pioneering Perception Policy with Reinforcement Learning","created":"2025-04-10","cited_by_count":120,"area":"lr"},{"id":"2502.06807","title":"Competitive Programming with Large Reasoning Models","created":"2025-02-03","cited_by_count":119,"area":"lr"},{"id":"2505.00127","title":"Between Underthinking and Overthinking: An Empirical Study of Reasoning Length and correctness in LLMs","created":"2025-04-30","cited_by_count":117,"area":"lr"},{"id":"2504.01943","title":"OpenCodeReasoning: Advancing Data Distillation for Competitive Coding","created":"2025-04-02","cited_by_count":113,"area":"lr"},{"id":"2505.13379","title":"Thinkless: LLM Learns When to Think","created":"2025-05-19","cited_by_count":113,"area":"lr"},{"id":"2506.02177","title":"Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts","created":"2025-06-02","cited_by_count":113,"area":"lr"},{"id":"2508.12790","title":"Reinforcement Learning with Rubric Anchors","created":"2025-08-18","cited_by_count":113,"area":"lr"},{"id":"2505.14970","title":"Self-Evolving Curriculum for LLM Reasoning","created":"2025-05-20","cited_by_count":112,"area":"lr"},{"id":"2504.00993","title":"MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs","created":"2025-04-01","cited_by_count":110,"area":"lr"},{"id":"2508.03680","title":"Agent Lightning: Train ANY AI Agents with Reinforcement Learning","created":"2025-08-05","cited_by_count":109,"area":"lr"},{"id":"2504.15279","title":"VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models","created":"2025-04-21","cited_by_count":107,"area":"lr"},{"id":"2501.18492","title":"GuardReasoner: Towards Reasoning-based LLM Safeguards","created":"2025-01-30","cited_by_count":100,"area":"lr"},{"id":"2503.20752","title":"Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models","created":"2025-03-26","cited_by_count":99,"area":"lr"},{"id":"2507.06448","title":"Perception-Aware Policy Optimization for Multimodal Reasoning","created":"2025-07-08","cited_by_count":99,"area":"lr"},{"id":"2506.07527","title":"Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions","created":"2025-06-09","cited_by_count":97,"area":"lr"},{"id":"2503.22342","title":"CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models","created":"2025-03-28","cited_by_count":96,"area":"lr"},{"id":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95,"area":"lr"},{"id":"2504.10903","title":"Efficient Reasoning Models: A Survey","created":"2025-04-15","cited_by_count":95,"area":"lr"},{"id":"2504.07086","title":"A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility","created":"2025-04-09","cited_by_count":93,"area":"lr"},{"id":"2505.12434","title":"VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning","created":"2025-05-18","cited_by_count":93,"area":"lr"},{"id":"2506.06632","title":"Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning","created":"2025-06-07","cited_by_count":92,"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":"2505.15107","title":"StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimization","created":"2025-05-21","cited_by_count":88,"area":"lr"},{"id":"2505.07686","title":"S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models","created":"2025-05-12","cited_by_count":87,"area":"lr"},{"id":"2505.11896","title":"AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning","created":"2025-05-17","cited_by_count":87,"area":"lr"},{"id":"2505.11409","title":"Visual Planning: Let's Think Only with Images","created":"2025-05-16","cited_by_count":85,"area":"lr"},{"id":"2505.16552","title":"Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains","created":"2025-05-22","cited_by_count":85,"area":"lr"},{"id":"2505.14231","title":"UniVG-R1: Reasoning Guided Universal Visual Grounding with Reinforcement Learning","created":"2025-05-20","cited_by_count":84,"area":"lr"},{"id":"2507.07966","title":"Scaling RL to Long Videos","created":"2025-07-10","cited_by_count":84,"area":"lr"},{"id":"2504.05185","title":"Concise Reasoning via Reinforcement Learning","created":"2025-04-07","cited_by_count":79,"area":"lr"},{"id":"2503.04548","title":"An Empirical Study on Eliciting and Improving R1-like Reasoning Models","created":"2025-03-06","cited_by_count":78,"area":"lr"},{"id":"2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","created":"2026-04-02","cited_by_count":76,"area":"lr"},{"id":"2505.10320","title":"J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning","created":"2025-05-15","cited_by_count":75,"area":"lr"},{"id":"2505.23564","title":"Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models","created":"2025-05-29","cited_by_count":75,"area":"lr"},{"id":"2503.16219","title":"Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't","created":"2025-03-20","cited_by_count":74,"area":"lr"},{"id":"2504.04823","title":"Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models","created":"2025-04-07","cited_by_count":73,"area":"lr"},{"id":"2504.21370","title":"ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning","created":"2025-04-30","cited_by_count":72,"area":"lr"},{"id":"2505.16410","title":"Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning","created":"2025-05-22","cited_by_count":72,"area":"lr"},{"id":"2504.05599","title":"Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought","created":"2025-04-08","cited_by_count":69,"area":"lr"},{"id":"2504.01903","title":"STAR-1: Safer Alignment of Reasoning LLMs with 1K Data","created":"2025-04-02","cited_by_count":68,"area":"lr"},{"id":"2504.14286","title":"SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM","created":"2025-04-19","cited_by_count":68,"area":"lr"}],"next_cursor":"100"}