{"total":72,"rows":[{"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":"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":"2505.00703","title":"T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT","created":"2025-05-01","cited_by_count":166,"area":"lr"},{"id":"2405.03553","title":"AlphaMath Almost Zero: Process Supervision without Process","created":"2024-05-06","cited_by_count":162,"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":"2406.10858","title":"Step-level Value Preference Optimization for Mathematical Reasoning","created":"2024-06-16","cited_by_count":72,"area":"lr"},{"id":"2407.09887","title":"OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling","created":"2024-07-13","cited_by_count":68,"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":"2506.05183","title":"TreeRPO: Tree Relative Policy Optimization","created":"2025-06-05","cited_by_count":46,"area":"lr"},{"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":"2505.10557","title":"MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning","created":"2025-05-15","cited_by_count":45,"area":"lr"},{"id":"2410.12896","title":"A Survey on Data Synthesis and Augmentation for Large Language Models","created":"2024-10-16","cited_by_count":41,"area":"synth"},{"id":"2410.09008","title":"SuperCorrect: Advancing Small LLM Reasoning with Thought Template Distillation and Self-Correction","created":"2024-10-11","cited_by_count":40,"area":"lr"},{"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":"2407.21009","title":"AI-Assisted Generation of Difficult Math Questions","created":"2024-07-30","cited_by_count":37,"area":"lr"},{"id":"2407.00782","title":"Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning","created":"2024-06-30","cited_by_count":35,"area":"lr"},{"id":"2411.12498","title":"Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus","created":"2024-11-19","cited_by_count":29,"area":"lr"},{"id":"2410.18693","title":"Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch","created":"2024-10-24","cited_by_count":24,"area":"lr"},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2503.17439","title":"LEMMA: Learning from Errors for MatheMatical Advancement in LLMs","created":"2025-03-21","cited_by_count":21,"area":"lr"},{"id":"2508.10975","title":"BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining","created":"2025-08-14","cited_by_count":21,"area":"synth"},{"id":"2510.23081","title":"A Survey on LLM Mid-Training","created":"2025-10-27","cited_by_count":21,"area":null},{"id":"2410.17635","title":"Markov Chain of Thought for Efficient Mathematical Reasoning","created":"2024-10-23","cited_by_count":19,"area":"lr"},{"id":"2505.13903","title":"Let's Verify Math Questions Step by Step","created":"2025-05-20","cited_by_count":18,"area":"lr"},{"id":"2404.14604","title":"Describe-then-Reason: Improving Multimodal Mathematical Reasoning through Visual Comprehension Training","created":"2024-04-22","cited_by_count":17,"area":"lr"},{"id":"2603.02218","title":"Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain","created":"2026-02-10","cited_by_count":17,"area":"synth"},{"id":"2503.02103","title":"Superficial Self-Improved Reasoners Benefit from Model Merging","created":"2025-03-03","cited_by_count":16,"area":"lr"},{"id":"2504.02953","title":"Cultural Learning-Based Culture Adaptation of Language Models","created":"2025-04-03","cited_by_count":16,"area":null},{"id":"2406.12050","title":"Learn Beyond The Answer: Training Language Models with Reflection for Mathematical Reasoning","created":"2024-06-17","cited_by_count":15,"area":"lr"},{"id":"2409.12929","title":"LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning","created":"2024-09-19","cited_by_count":14,"area":"lr"},{"id":"2501.01478","title":"Enhancing Reasoning through Process Supervision with Monte Carlo Tree Search","created":"2025-01-02","cited_by_count":14,"area":"lr"},{"id":"2502.13137","title":"Theorem Prover as a Judge for Synthetic Data Generation","created":"2025-02-18","cited_by_count":14,"area":"lr"},{"id":"2410.22316","title":"Understanding Synthetic Context Extension via Retrieval Heads","created":"2024-10-29","cited_by_count":10,"area":"rag"},{"id":"2510.04081","title":"Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning","created":"2025-10-05","cited_by_count":10,"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":"2412.16964","title":"System-2 Mathematical Reasoning via Enriched Instruction Tuning","created":"2024-12-22","cited_by_count":7,"area":"lr"},{"id":"2507.04391","title":"Does Learning Mathematical Problem-Solving Generalize to Broader Reasoning?","created":"2025-07-06","cited_by_count":7,"area":"lr"},{"id":"2510.19361","title":"AgenticMath: Enhancing LLM Reasoning via Agentic-based Math Data Generation","created":"2025-10-22","cited_by_count":7,"area":"lr"},{"id":"2408.15565","title":"SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models","created":"2024-08-28","cited_by_count":6,"area":"lr"},{"id":"2505.12766","title":"Reasoning-OCR: Can Large Multimodal Models Solve Complex Logical Reasoning Problems from OCR Cues?","created":"2025-05-19","cited_by_count":6,"area":"lr"},{"id":"2509.21070","title":"ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning","created":"2025-09-25","cited_by_count":6,"area":"lr"},{"id":"2602.12036","title":"Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2503.13992","title":"The KoLMogorov Test: Compression by Code Generation","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2504.14775","title":"gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling","created":"2025-04-21","cited_by_count":5,"area":"inference"},{"id":"2503.21332","title":"ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2508.19532","title":"Alignment with Fill-In-the-Middle for Enhancing Code Generation","created":"2025-08-27","cited_by_count":4,"area":"alignment"},{"id":"2411.19039","title":"Mars-PO: Multi-Agent Reasoning System Preference Optimization","created":"2024-11-28","cited_by_count":3,"area":"lr"},{"id":"2502.11466","title":"GiFT: Gibbs Fine-Tuning for Code Generation","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2509.13079","title":"When Inverse Data Outperforms: Exploring the Pitfalls of Mixed Data in Multi-Stage Fine-Tuning","created":"2025-09-16","cited_by_count":2,"area":"alignment"},{"id":"2603.13309","title":"Preventing Curriculum Collapse in Self-Evolving Reasoning Systems","created":"2026-03-03","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":"2403.14562","title":"Agentic AI: The Era of Semantic Decoding","created":"2024-03-21","cited_by_count":1,"area":"agents"},{"id":"2502.20855","title":"MAMUT: A Novel Framework for Modifying Mathematical Formulas for the Generation of Specialized Datasets for Language Model Training","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2504.02671","title":"LLM for Complex Reasoning Task: An Exploratory Study in Fermi Problems","created":"2025-04-03","cited_by_count":1,"area":"lr"},{"id":"2504.20426","title":"RV-Syn: Rational and Verifiable Mathematical Reasoning Data Synthesis based on Structured Function Library","created":"2025-04-29","cited_by_count":1,"area":"lr"},{"id":"2601.17006","title":"MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning","created":"2026-01-14","cited_by_count":1,"area":"lr"},{"id":"2602.19069","title":"Asking the Right Questions: Improving Reasoning with Generated Stepping Stones","created":"2026-02-22","cited_by_count":1,"area":"lr"},{"id":"2604.16804","title":"AutoOR: Scalably Post-training LLMs to Autoformulate Operations Research Problems","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2609.36903","title":"MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2502.08904","title":"MIH-TCCT: Mitigating Inconsistent Hallucinations in LLMs via Event-Driven Text-Code Cyclic Training","created":"2025-02-13","cited_by_count":0,"area":null},{"id":"2506.15706","title":"MDPO: Multi-Granularity Direct Preference Optimization for Mathematical Reasoning","created":"2025-05-30","cited_by_count":0,"area":"lr"},{"id":"2507.16478","title":"ACT: Bridging the Gap in Code Translation through Synthetic Data Generation & Adaptive Training","created":"2025-07-22","cited_by_count":0,"area":"synth"},{"id":"2508.15180","title":"PuzzleClone: A DSL-Powered Framework for Synthesizing Verifiable Data","created":"2025-08-21","cited_by_count":0,"area":"lr"},{"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":"2512.02791","title":"Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2602.03300","title":"R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?","created":"2026-02-03","cited_by_count":0,"area":"mllm"},{"id":"2602.20296","title":"Learning to Solve Complex Problems via Dataset Decomposition","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.08291","title":"A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning","created":"2026-03-09","cited_by_count":0,"area":"lr"},{"id":"2605.21160","title":"Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2605.23933","title":"KT4EQG: Personalized Exercise Question Generation via Knowledge Tracing","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2607.22883","title":"Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2609.01386","title":"When Tokenization is Secretly Output Supervision","created":"2026-09-01","cited_by_count":0,"area":null}],"next_cursor":null}