{"total":81,"rows":[{"id":"2409.12122","title":"Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement","created":"2024-09-18","cited_by_count":1090,"area":"synth"},{"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":"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":"2504.13958","title":"ToolRL: Reward is All Tool Learning Needs","created":"2025-04-16","cited_by_count":362,"area":"agents"},{"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":"2406.18629","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","created":"2024-06-26","cited_by_count":273,"area":"lr"},{"id":"2504.16891","title":"AIMO-2 Winning Solution: Building State-of-the-Art Mathematical Reasoning Models with OpenMathReasoning dataset","created":"2025-04-23","cited_by_count":174,"area":"lr"},{"id":"2503.23383","title":"ToRL: Scaling Tool-Integrated RL","created":"2025-03-30","cited_by_count":169,"area":"agents"},{"id":"2405.03553","title":"AlphaMath Almost Zero: Process Supervision without Process","created":"2024-05-06","cited_by_count":162,"area":"lr"},{"id":"2402.10176","title":"OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset","created":"2024-02-15","cited_by_count":143,"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":"2407.13690","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","created":"2024-06-18","cited_by_count":95,"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":"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":"2406.10858","title":"Step-level Value Preference Optimization for Mathematical Reasoning","created":"2024-06-16","cited_by_count":72,"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":"2502.06772","title":"ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates","created":"2025-02-10","cited_by_count":63,"area":"lr"},{"id":"2505.14246","title":"Visual Agentic Reinforcement Fine-Tuning","created":"2025-05-20","cited_by_count":55,"area":"lr"},{"id":"2502.19411","title":"Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs","created":"2025-02-26","cited_by_count":47,"area":"lr"},{"id":"2503.19551","title":"Scaling Laws of Synthetic Data for Language Models","created":"2025-03-25","cited_by_count":46,"area":"synth"},{"id":"2405.14365","title":"JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models","created":"2024-05-23","cited_by_count":45,"area":"lr"},{"id":"2505.11792","title":"Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling","created":"2025-05-17","cited_by_count":45,"area":null},{"id":"2410.08196","title":"MathCoder2: Better Math Reasoning from Continued Pretraining on Model-translated Mathematical Code","created":"2024-10-10","cited_by_count":39,"area":"lr"},{"id":"2502.12853","title":"S$^2$R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning","created":"2025-02-18","cited_by_count":39,"area":"lr"},{"id":"2510.11701","title":"Demystifying Reinforcement Learning in Agentic Reasoning","created":"2025-10-13","cited_by_count":33,"area":"lr"},{"id":"2502.00691","title":"To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization","created":"2025-02-02","cited_by_count":25,"area":"lr"},{"id":"2503.03746","title":"Process-based Self-Rewarding Language Models","created":"2025-03-05","cited_by_count":22,"area":"lr"},{"id":"2410.18792","title":"An LLM Agent for Automatic Geospatial Data Analysis","created":"2024-10-24","cited_by_count":21,"area":"agents"},{"id":"2601.03555","title":"SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models","created":"2026-01-07","cited_by_count":21,"area":"alignment"},{"id":"2410.17635","title":"Markov Chain of Thought for Efficient Mathematical Reasoning","created":"2024-10-23","cited_by_count":19,"area":"lr"},{"id":"2507.09662","title":"Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey","created":"2025-07-13","cited_by_count":18,"area":"lr"},{"id":"2411.11504","title":"Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering","created":"2024-11-18","cited_by_count":16,"area":null},{"id":"2604.16004","title":"AgentV-RL: Scaling Reward Modeling with Agentic Verifier","created":"2026-04-17","cited_by_count":15,"area":"lr"},{"id":"2404.13925","title":"MARIO Eval: Evaluate Your Math LLM with your Math LLM--A mathematical dataset evaluation toolkit","created":"2024-04-22","cited_by_count":14,"area":null},{"id":"2502.14356","title":"Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning","created":"2025-02-20","cited_by_count":14,"area":"lr"},{"id":"2509.26578","title":"Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning","created":"2025-09-30","cited_by_count":14,"area":"lr"},{"id":"2503.04618","title":"Better Process Supervision with Bi-directional Rewarding Signals","created":"2025-03-06","cited_by_count":12,"area":"lr"},{"id":"2502.14333","title":"A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematics","created":"2025-02-20","cited_by_count":11,"area":"lr"},{"id":"2506.04108","title":"Rectified Sparse Attention","created":"2025-06-04","cited_by_count":10,"area":"inference"},{"id":"2507.14783","title":"Omni-Thinker: Scaling Multi-Task RL in LLMs with Hybrid Reward and Task Scheduling","created":"2025-07-20","cited_by_count":10,"area":"lr"},{"id":"2509.21826","title":"ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models","created":"2025-09-26","cited_by_count":10,"area":null},{"id":"2506.19847","title":"Orthogonal Finetuning Made Scalable","created":"2025-06-24","cited_by_count":7,"area":null},{"id":"2502.14619","title":"Reward Models Identify Consistency, Not Causality","created":"2025-02-20","cited_by_count":6,"area":"alignment"},{"id":"2502.17956","title":"Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments","created":"2025-02-25","cited_by_count":6,"area":"lr"},{"id":"2502.20186","title":"Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledge","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2503.14891","title":"MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer","created":"2025-03-19","cited_by_count":6,"area":"lr"},{"id":"2601.18533","title":"From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation","created":"2026-01-26","cited_by_count":6,"area":"alignment"},{"id":"2604.09813","title":"Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning","created":"2026-04-10","cited_by_count":6,"area":"agents"},{"id":"2410.13510","title":"GeoCoder: Solving Geometry Problems by Generating Modular Code through Vision-Language Models","created":"2024-10-17","cited_by_count":5,"area":"lr"},{"id":"2504.07527","title":"Supervised Optimism Correction: Be Confident When LLMs Are Sure","created":"2025-04-10","cited_by_count":5,"area":null},{"id":"2505.23851","title":"ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark","created":"2025-05-28","cited_by_count":5,"area":null},{"id":"2602.04541","title":"LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding","created":"2026-02-04","cited_by_count":5,"area":"inference"},{"id":"2503.00812","title":"BOSE: A Systematic Evaluation Method Optimized for Base Models","created":"2025-03-02","cited_by_count":4,"area":null},{"id":"2506.07751","title":"AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking","created":"2025-06-09","cited_by_count":4,"area":"lr"},{"id":"2502.13516","title":"SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin","created":"2025-02-19","cited_by_count":3,"area":"lr"},{"id":"2510.15979","title":"Cog-Rethinker: Hierarchical Metacognitive Reinforcement Learning for LLM Reasoning","created":"2025-10-13","cited_by_count":3,"area":"lr"},{"id":"2606.16215","title":"PACT: Privileged Trace Co-Training for Multi-Turn Tool-Use Agents","created":"2026-06-15","cited_by_count":3,"area":null},{"id":"2608.27260","title":"What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents","created":"2026-08-27","cited_by_count":3,"area":"agents"},{"id":"2505.20700","title":"Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration","created":"2025-05-27","cited_by_count":2,"area":"lr"},{"id":"2507.19399","title":"Running in CIRCLE? A Simple Benchmark for LLM Code Interpreter Security","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2604.01220","title":"Universal YOCO for Efficient Depth Scaling","created":"2026-04-01","cited_by_count":2,"area":"lr"},{"id":"2604.08281","title":"When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"id":"2604.11188","title":"MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis","created":"2026-04-13","cited_by_count":2,"area":"lr"},{"id":"2605.09931","title":"PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2607.13248","title":"GSM-Plus-BN: A Perturbation-Based Benchmark for Bangla Mathematical Reasoning in Large Language Models","created":"2026-07-14","cited_by_count":2,"area":"lr"},{"id":"2411.19547","title":"Training Agents with Weakly Supervised Feedback from Large Language Models","created":"2024-11-29","cited_by_count":1,"area":"agents"},{"id":"2505.14419","title":"SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation","created":"2025-05-20","cited_by_count":1,"area":"lr"},{"id":"2509.19893","title":"Future Policy Approximation for Offline Reinforcement Learning in LLM Reasoning","created":"2025-09-24","cited_by_count":1,"area":"lr"},{"id":"2601.22730","title":"ImgCoT: Compressing Long Chain of Thought into Compact Visual Tokens for Efficient Reasoning of Large Language Model","created":"2026-01-30","cited_by_count":1,"area":"lr"},{"id":"2603.18756","title":"Are complicated loss functions necessary for teaching LLMs to reason?","created":"2026-03-19","cited_by_count":1,"area":"lr"},{"id":"2604.06377","title":"The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment","created":"2026-04-07","cited_by_count":1,"area":"lr"},{"id":"2608.03545","title":"Hi-TTRL: Regulating Consensus with Hints for Test-Time Reinforcement Learning","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2507.22411","title":"NeedleChain: Measuring Intact Context Comprehension Capability of Large Language Models","created":"2025-07-30","cited_by_count":0,"area":null},{"id":"2510.25310","title":"Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoning","created":"2025-10-29","cited_by_count":0,"area":"lr"},{"id":"2602.01207","title":"Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment","created":"2026-02-01","cited_by_count":0,"area":"lr"},{"id":"2604.14768","title":"CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning","created":"2026-04-16","cited_by_count":0,"area":"lr"},{"id":"2605.26246","title":"The Bridge-Garden Dilemma in LLM Distillation: Why Mixing Hard and Soft Labels Works","created":"2026-05-25","cited_by_count":0,"area":"distill"},{"id":"2608.22806","title":"DIAG: Diagnostic Iterative Alignment and Generation for Data-Efficient Mathematical Preference Distillation","created":"2026-08-24","cited_by_count":0,"area":"lr"},{"id":"2609.01386","title":"When Tokenization is Secretly Output Supervision","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.39220","title":"Learning Process Rewards via Reasoning State Propagation","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.01896","title":"Asynchronous LLM Post-Training: Group-Mass Capping and Convergence Analysis","created":"2026-10-01","cited_by_count":0,"area":"lr"}],"next_cursor":null}