{"total":1090,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820,"area":"lr"},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942,"area":"moe"},{"id":"2503.20783","title":"Understanding R1-Zero-Like Training: A Critical Perspective","created":"2025-03-26","cited_by_count":1345,"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":"2502.03387","title":"LIMO: Less is More for Reasoning","created":"2025-02-05","cited_by_count":498,"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":"2501.07301","title":"The Lessons of Developing Process Reward Models in Mathematical Reasoning","created":"2025-01-13","cited_by_count":415,"area":"lr"},{"id":"2504.11536","title":"ReTool: Reinforcement Learning for Strategic Tool Use in LLMs","created":"2025-04-15","cited_by_count":392,"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":"2505.03335","title":"Absolute Zero: Reinforced Self-play Reasoning with Zero Data","created":"2025-05-06","cited_by_count":344,"area":"lr"},{"id":"2501.04519","title":"rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking","created":"2025-01-08","cited_by_count":313,"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":"2412.06559","title":"ProcessBench: Identifying Process Errors in Mathematical Reasoning","created":"2024-12-09","cited_by_count":292,"area":"lr"},{"id":"2410.07985","title":"Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models","created":"2024-10-10","cited_by_count":284,"area":"lr"},{"id":"2504.14945","title":"Learning to Reason under Off-Policy Guidance","created":"2025-04-21","cited_by_count":281,"area":"lr"},{"id":"2506.14758","title":"Reasoning with Exploration: An Entropy Perspective","created":"2025-06-17","cited_by_count":281,"area":"lr"},{"id":"2505.24298","title":"AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning","created":"2025-05-30","cited_by_count":250,"area":"lr"},{"id":"2506.10947","title":"Spurious Rewards: Rethinking Training Signals in RLVR","created":"2025-06-12","cited_by_count":209,"area":"lr"},{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2503.23383","title":"ToRL: Scaling Tool-Integrated RL","created":"2025-03-30","cited_by_count":169,"area":"agents"},{"id":"2505.15134","title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","created":"2025-05-21","cited_by_count":166,"area":"lr"},{"id":"2501.15383","title":"Qwen2.5-1M Technical Report","created":"2025-01-26","cited_by_count":164,"area":null},{"id":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155,"area":"safety"},{"id":"2506.09038","title":"AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions","created":"2025-06-10","cited_by_count":145,"area":"lr"},{"id":"2502.11886","title":"LIMR: Less is More for RL Scaling","created":"2025-02-17","cited_by_count":139,"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":"2505.14652","title":"General-Reasoner: Advancing LLM Reasoning Across All Domains","created":"2025-05-20","cited_by_count":135,"area":"lr"},{"id":"2501.05444","title":"Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark","created":"2025-01-09","cited_by_count":134,"area":"lr"},{"id":"2504.05812","title":"Right Question is Already Half the Answer: Fully Unsupervised LLM Reasoning Incentivization","created":"2025-04-08","cited_by_count":128,"area":"lr"},{"id":"2502.18080","title":"Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning","created":"2025-02-25","cited_by_count":119,"area":"lr"},{"id":"2503.02951","title":"KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Coding","created":"2025-03-04","cited_by_count":119,"area":"lr"},{"id":"2502.12143","title":"Small Models Struggle to Learn from Strong Reasoners","created":"2025-02-17","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":"2506.20512","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","created":"2025-06-25","cited_by_count":113,"area":"lr"},{"id":"2504.09037","title":"A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems","created":"2025-04-12","cited_by_count":111,"area":"lr"},{"id":"2507.20673","title":"Geometric-Mean Policy Optimization","created":"2025-07-28","cited_by_count":111,"area":"lr"},{"id":"2501.19324","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning","created":"2025-01-31","cited_by_count":106,"area":"lr"},{"id":"2504.03380","title":"Online Difficulty Filtering for Reasoning Oriented Reinforcement Learning","created":"2025-04-04","cited_by_count":104,"area":"lr"},{"id":"2501.03124","title":"PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models","created":"2025-01-06","cited_by_count":99,"area":"lr"},{"id":"2502.20122","title":"Self-Training Elicits Concise Reasoning in Large Language Models","created":"2025-02-27","cited_by_count":99,"area":"lr"},{"id":"2503.22679","title":"Q-Insight: Understanding Image Quality via Visual Reinforcement Learning","created":"2025-03-28","cited_by_count":98,"area":null},{"id":"2504.00891","title":"GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning","created":"2025-04-01","cited_by_count":97,"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":"2503.02318","title":"Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models","created":"2025-03-04","cited_by_count":95,"area":"lr"},{"id":"2410.09671","title":"OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models","created":"2024-10-12","cited_by_count":94,"area":"lr"},{"id":"2502.01718","title":"ACECODER: Acing Coder RL via Automated Test-Case Synthesis","created":"2025-02-03","cited_by_count":93,"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":"2411.16489","title":"O1 Replication Journey -- Part 2: Surpassing O1-preview through Simple Distillation, Big Progress or Bitter Lesson?","created":"2024-11-25","cited_by_count":92,"area":"lr"},{"id":"2410.02884","title":"LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning","created":"2024-10-03","cited_by_count":91,"area":"lr"},{"id":"2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","created":"2025-08-15","cited_by_count":91,"area":"lr"},{"id":"2505.03318","title":"Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning","created":"2025-05-06","cited_by_count":90,"area":"lr"},{"id":"2506.03106","title":"Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback","created":"2025-06-03","cited_by_count":90,"area":"lr"},{"id":"2502.06453","title":"MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations","created":"2025-02-10","cited_by_count":89,"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":"2410.15115","title":"On Designing Effective RL Reward at Training Time for LLM Reasoning","created":"2024-10-19","cited_by_count":87,"area":"lr"},{"id":"2505.16400","title":"AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning","created":"2025-05-22","cited_by_count":87,"area":"lr"},{"id":"2502.03438","title":"BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving","created":"2025-02-05","cited_by_count":84,"area":null},{"id":"2502.13124","title":"NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions","created":"2025-02-18","cited_by_count":84,"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":"2506.19767","title":"SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning","created":"2025-06-24","cited_by_count":84,"area":"lr"},{"id":"2504.09696","title":"GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models","created":"2025-04-13","cited_by_count":82,"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":"2410.10347","title":"A Unified Approach to Routing and Cascading for LLMs","created":"2024-10-14","cited_by_count":80,"area":"agents"},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79,"area":"lr"},{"id":"2412.15084","title":"AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling","created":"2024-12-19","cited_by_count":77,"area":"lr"},{"id":"2501.11651","title":"T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling","created":"2025-01-20","cited_by_count":77,"area":"lr"},{"id":"2505.21493","title":"Reinforcing General Reasoning without Verifiers","created":"2025-05-27","cited_by_count":77,"area":"lr"},{"id":"2506.13284","title":"AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy","created":"2025-06-16","cited_by_count":77,"area":"lr"},{"id":"2507.22034","title":"UserBench: An Interactive Gym Environment for User-Centric Agents","created":"2025-07-29","cited_by_count":76,"area":"agents"},{"id":"2505.15612","title":"Learn to Reason Efficiently with Adaptive Length-based Reward Shaping","created":"2025-05-21","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":"2510.05592","title":"In-the-Flow Agentic System Optimization for Effective Planning and Tool Use","created":"2025-10-07","cited_by_count":72,"area":"lr"},{"id":"2502.12215","title":"Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?","created":"2025-02-17","cited_by_count":70,"area":"lr"},{"id":"2502.19613","title":"Self-rewarding correction for mathematical reasoning","created":"2025-02-26","cited_by_count":70,"area":"lr"},{"id":"2503.21380","title":"Challenging the Boundaries of Reasoning: An Olympiad-Level Math Benchmark for Large Language Models","created":"2025-03-27","cited_by_count":70,"area":"lr"},{"id":"2506.13654","title":"Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning","created":"2025-06-16","cited_by_count":68,"area":"lr"},{"id":"2505.14631","title":"Think Only When You Need with Large Hybrid-Reasoning Models","created":"2025-05-20","cited_by_count":66,"area":"lr"},{"id":"2412.13147","title":"Are Your LLMs Capable of Stable Reasoning?","created":"2024-12-17","cited_by_count":65,"area":"lr"},{"id":"2501.04686","title":"Unlocking Multimodal Mathematical Reasoning via Process Reward Model","created":"2025-01-08","cited_by_count":65,"area":"lr"},{"id":"2501.17703","title":"Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate","created":"2025-01-29","cited_by_count":63,"area":"lr"},{"id":"2502.06772","title":"ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates","created":"2025-02-10","cited_by_count":63,"area":"lr"},{"id":"2502.12289","title":"Evaluating Step-by-step Reasoning Traces: A Survey","created":"2025-02-17","cited_by_count":63,"area":"lr"},{"id":"2505.07773","title":"Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solving","created":"2025-05-12","cited_by_count":62,"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":"2504.16074","title":"PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models","created":"2025-04-22","cited_by_count":61,"area":"lr"},{"id":"2510.03215","title":"Cache-to-Cache: Direct Semantic Communication Between Large Language Models","created":"2025-10-03","cited_by_count":61,"area":"inference"},{"id":"2507.01679","title":"Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling","created":"2025-07-02","cited_by_count":60,"area":"lr"},{"id":"2502.12054","title":"PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning","created":"2025-02-17","cited_by_count":59,"area":"lr"},{"id":"2504.18428","title":"PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts","created":"2025-04-25","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":"2412.11936","title":"A Survey of Mathematical Reasoning in the Era of Multimodal Large Language Model: Benchmark, Method & Challenges","created":"2024-12-16","cited_by_count":55,"area":"lr"},{"id":"2502.07316","title":"CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction","created":"2025-02-11","cited_by_count":55,"area":"lr"},{"id":"2503.06692","title":"InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models","created":"2025-03-09","cited_by_count":54,"area":"lr"},{"id":"2502.02508","title":"Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search","created":"2025-02-04","cited_by_count":53,"area":"lr"},{"id":"2510.01161","title":"Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?","created":"2025-10-01","cited_by_count":53,"area":"lr"}],"next_cursor":"100"}