{"total":57,"rows":[{"id":"2309.15402","title":"Navigate through Enigmatic Labyrinth A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future","created":"2023-09-27","cited_by_count":184,"area":"lr"},{"id":"2502.19634","title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning","created":"2025-02-26","cited_by_count":173,"area":"lr"},{"id":"2407.06023","title":"Distilling System 2 into System 1","created":"2024-07-08","cited_by_count":159,"area":"lr"},{"id":"2402.13950","title":"Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoning","created":"2024-02-21","cited_by_count":110,"area":"lr"},{"id":"2309.06979","title":"Auto-Regressive Next-Token Predictors are Universal Learners","created":"2023-09-13","cited_by_count":67,"area":"lr"},{"id":"2406.02537","title":"TopViewRS: Vision-Language Models as Top-View Spatial Reasoners","created":"2024-06-04","cited_by_count":49,"area":"lr"},{"id":"2404.15676","title":"Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs","created":"2024-04-24","cited_by_count":48,"area":"lr"},{"id":"2402.04616","title":"Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation","created":"2024-02-07","cited_by_count":47,"area":"lr"},{"id":"2309.04461","title":"Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models","created":"2023-09-08","cited_by_count":45,"area":"lr"},{"id":"2503.17523","title":"Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models","created":"2025-03-21","cited_by_count":37,"area":"lr"},{"id":"2410.06238","title":"EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration","created":"2024-10-08","cited_by_count":34,"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":"2310.10845","title":"CoTFormer: A Chain-of-Thought Driven Architecture with Budget-Adaptive Computation Cost at Inference","created":"2023-10-16","cited_by_count":27,"area":"lr"},{"id":"2312.05562","title":"Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models","created":"2023-12-09","cited_by_count":27,"area":"lr"},{"id":"2308.06207","title":"Thinking Like an Expert:Multimodal Hypergraph-of-Thought (HoT) Reasoning to boost Foundation Modals","created":"2023-08-11","cited_by_count":24,"area":"lr"},{"id":"2403.03348","title":"Learning to Maximize Mutual Information for Chain-of-Thought Distillation","created":"2024-03-05","cited_by_count":23,"area":"lr"},{"id":"2312.10730","title":"Mixed Distillation Helps Smaller Language Model Better Reasoning","created":"2023-12-17","cited_by_count":19,"area":"lr"},{"id":"2403.16385","title":"Synthesize Step-by-Step: Tools, Templates and LLMs as Data Generators for Reasoning-Based Chart VQA","created":"2024-03-25","cited_by_count":19,"area":"lr"},{"id":"2402.15000","title":"Divide-or-Conquer? Which Part Should You Distill Your LLM?","created":"2024-02-22","cited_by_count":17,"area":"lr"},{"id":"2409.01281","title":"Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs","created":"2024-08-25","cited_by_count":17,"area":"lr"},{"id":"2406.14511","title":"Investigating Mysteries of CoT-Augmented Distillation","created":"2024-06-20","cited_by_count":16,"area":"lr"},{"id":"2410.10336","title":"CoMAT: Chain of Mathematically Annotated Thought Improves Mathematical Reasoning","created":"2024-10-14","cited_by_count":16,"area":"lr"},{"id":"2310.04921","title":"Crystal: Introspective Reasoners Reinforced with Self-Feedback","created":"2023-10-07","cited_by_count":15,"area":"lr"},{"id":"2404.03414","title":"Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought","created":"2024-04-04","cited_by_count":12,"area":"lr"},{"id":"2407.03181","title":"Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs","created":"2024-07-03","cited_by_count":12,"area":"lr"},{"id":"2502.19557","title":"Distill Not Only Data but Also Rewards: Can Smaller Language Models Surpass Larger Ones?","created":"2025-02-26","cited_by_count":12,"area":"lr"},{"id":"2503.10167","title":"\"Well, Keep Thinking\": Enhancing LLM Reasoning with Adaptive Injection Decoding","created":"2025-03-13","cited_by_count":12,"area":"lr"},{"id":"2508.16861","title":"Learning from Diverse Reasoning Paths with Routing and Collaboration","created":"2025-08-23","cited_by_count":12,"area":"lr"},{"id":"2504.00424","title":"Hawkeye:Efficient Reasoning with Model Collaboration","created":"2025-04-01","cited_by_count":11,"area":"lr"},{"id":"2510.25992","title":"Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning","created":"2025-10-29","cited_by_count":11,"area":"lr"},{"id":"2505.18759","title":"The Quest for Efficient Reasoning: A Data-Centric Benchmark to CoT Distillation","created":"2025-05-24","cited_by_count":9,"area":"lr"},{"id":"2403.09085","title":"Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance","created":"2024-03-14","cited_by_count":8,"area":"lr"},{"id":"2505.20072","title":"Incentivizing Strong Reasoning from Weak Supervision","created":"2025-05-26","cited_by_count":8,"area":"lr"},{"id":"2509.23574","title":"Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales","created":"2025-09-28","cited_by_count":8,"area":"lr"},{"id":"2509.08814","title":"Merge-of-Thought Distillation","created":"2025-09-10","cited_by_count":7,"area":"lr"},{"id":"2509.05602","title":"Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation","created":"2025-09-06","cited_by_count":6,"area":"lr"},{"id":"2409.10007","title":"SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL","created":"2024-09-16","cited_by_count":4,"area":"lr"},{"id":"2506.06470","title":"SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2510.05871","title":"Towards Label-Free Biological Reasoning Synthetic Dataset Creation via Uncertainty Filtering","created":"2025-10-07","cited_by_count":3,"area":"lr"},{"id":"2402.03175","title":"Beyond the Black Box: A Statistical Model for LLM Reasoning and Inference","created":"2024-02-05","cited_by_count":2,"area":"lr"},{"id":"2308.04711","title":"Answering Unseen Questions With Smaller Language Models Using Rationale Generation and Dense Retrieval","created":"2023-08-09","cited_by_count":1,"area":"lr"},{"id":"2309.09809","title":"A Stepwise Distillation Learning Strategy for Non-differentiable Visual Programming Frameworks on Visual Reasoning Tasks","created":"2023-09-18","cited_by_count":1,"area":"lr"},{"id":"2603.19266","title":"Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion","created":"2026-02-26","cited_by_count":1,"area":"lr"},{"id":"2605.04078","title":"Validity-Calibrated Reasoning Distillation","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2507.04893","title":"MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Prediction","created":"2025-07-07","cited_by_count":0,"area":"lr"},{"id":"2508.05234","title":"Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation","created":"2025-08-07","cited_by_count":0,"area":"lr"},{"id":"2509.12476","title":"Audited Reasoning Refinement: Fine-Tuning Language Models via LLM-Guided Step-Wise Evaluation and Correction","created":"2025-09-15","cited_by_count":0,"area":"lr"},{"id":"2509.16561","title":"SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoning","created":"2025-09-20","cited_by_count":0,"area":"lr"},{"id":"2512.06859","title":"JT-DA: Enhancing Data Analysis with Tool-Integrated Table Reasoning Large Language Models","created":"2025-12-07","cited_by_count":0,"area":"lr"},{"id":"2601.10987","title":"Reasoning Distillation for Lightweight Automated Program Repair","created":"2026-01-16","cited_by_count":0,"area":"lr"},{"id":"2603.01641","title":"Learning Structured Reasoning via Tractable Trajectory Control","created":"2026-03-02","cited_by_count":0,"area":"lr"},{"id":"2605.07139","title":"Structural Rationale Distillation via Reasoning Space Compression","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2607.05734","title":"SCOReD: Student-Aware CoT Optimization for Recommendation Distillation","created":"2026-07-07","cited_by_count":0,"area":"lr"},{"id":"2607.28680","title":"TELLER: Dual-Path Iterative Preference Optimization for Table Entity Linking","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2609.16255","title":"Efficient Reasoning Distillation: Small Video-Language Models via Synthetic CoT and Difficulty-Aware Fine-Tuning","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2610.12933","title":"Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.19871","title":"Rationale Distribution Distillation via Flow Matching for Distributional Continuous Latent Reasoning","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}