{"total":37,"rows":[{"id":"2406.09136","title":"Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs","created":"2024-06-13","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":"2507.16746","title":"Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning","created":"2025-07-22","cited_by_count":84,"area":"lr"},{"id":"2411.19943","title":"Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability","created":"2024-11-29","cited_by_count":83,"area":"lr"},{"id":"2410.11287","title":"Process Reward Model with Q-Value Rankings","created":"2024-10-15","cited_by_count":80,"area":"lr"},{"id":"2410.16033","title":"TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Sampling","created":"2024-10-18","cited_by_count":61,"area":"lr"},{"id":"2506.08446","title":"A Survey on Large Language Models for Mathematical Reasoning","created":"2025-06-10","cited_by_count":52,"area":"lr"},{"id":"2504.12329","title":"Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time","created":"2025-04-12","cited_by_count":48,"area":"lr"},{"id":"2506.21656","title":"Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs","created":"2025-06-26","cited_by_count":32,"area":"lr"},{"id":"2410.15595","title":"A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applications","created":"2024-10-21","cited_by_count":27,"area":"lr"},{"id":"2508.02298","title":"CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment","created":"2025-08-04","cited_by_count":26,"area":"lr"},{"id":"2408.13518","title":"Selective Preference Optimization via Token-Level Reward Function Estimation","created":"2024-08-24","cited_by_count":25,"area":"lr"},{"id":"2502.10867","title":"A Tutorial on LLM Reasoning: Relevant Methods behind ChatGPT o1","created":"2025-02-15","cited_by_count":25,"area":"lr"},{"id":"2510.00194","title":"GRPO-$\\lambda$: Credit Assignment improves LLM Reasoning","created":"2025-09-30","cited_by_count":23,"area":"lr"},{"id":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2504.04524","title":"Trust Region Preference Approximation: A simple and stable reinforcement learning algorithm for LLM reasoning","created":"2025-04-06","cited_by_count":12,"area":"lr"},{"id":"2512.07533","title":"VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection","created":"2025-12-08","cited_by_count":11,"area":"lr"},{"id":"2510.03595","title":"Decoupling Task-Solving and Output Formatting in LLM Generation","created":"2025-10-04","cited_by_count":9,"area":"lr"},{"id":"2503.23371","title":"FeRG-LLM : Feature Engineering by Reason Generation Large Language Models","created":"2025-03-30","cited_by_count":8,"area":"lr"},{"id":"2510.03865","title":"Unlocking Reasoning Capabilities in LLMs via Reinforcement Learning Exploration","created":"2025-10-04","cited_by_count":7,"area":"lr"},{"id":"2605.03327","title":"DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment","created":"2026-05-05","cited_by_count":7,"area":"lr"},{"id":"2602.11455","title":"Credit Where It is Due: Cross-Modality Connectivity Drives Precise Reinforcement Learning for MLLM Reasoning","created":"2026-02-12","cited_by_count":6,"area":"lr"},{"id":"2605.00380","title":"ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning","created":"2026-05-01","cited_by_count":6,"area":"lr"},{"id":"2606.29150","title":"Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners","created":"2026-06-28","cited_by_count":6,"area":"lr"},{"id":"2510.13170","title":"Putting on the Thinking Hats: A Survey on Chain of Thought Fine-tuning from the Perspective of Human Reasoning Mechanism","created":"2025-10-15","cited_by_count":4,"area":"lr"},{"id":"2606.20008","title":"VIMPO: Value-Implicit Policy Optimization for LLMs","created":"2026-06-18","cited_by_count":4,"area":"lr"},{"id":"2505.23540","title":"Probability-Consistent Preference Optimization for Enhanced LLM Reasoning","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2502.18532","title":"CuDIP: Enhancing Theorem Proving in LLMs via Curriculum Learning-based Direct Preference Optimization","created":"2025-02-25","cited_by_count":1,"area":"lr"},{"id":"2602.07832","title":"rePIRL: Learn PRM with Inverse RL for LLM Reasoning","created":"2026-02-08","cited_by_count":1,"area":"lr"},{"id":"2603.29871","title":"ShapE-GRPO: Shapley-Enhanced Reward Allocation for Multi-Candidate LLM Training","created":"2026-03-31","cited_by_count":1,"area":"lr"},{"id":"2604.19857","title":"Rethinking Reinforcement Fine-Tuning in LVLM: Convergence, Reward Decomposition, and Generalization","created":"2026-04-21","cited_by_count":1,"area":"lr"},{"id":"2606.08035","title":"DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning","created":"2026-06-06","cited_by_count":1,"area":"lr"},{"id":"2510.21093","title":"MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning","created":"2025-10-24","cited_by_count":0,"area":"lr"},{"id":"2512.13668","title":"A Scientific Reasoning Model for Organic Synthesis Procedure Generation","created":"2025-12-15","cited_by_count":0,"area":"lr"},{"id":"2605.14071","title":"Distribution Corrected Offline Data Distillation for Large Language Models","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2607.03166","title":"KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2609.15987","title":"Bellman Policy Optimization","created":"2026-09-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}