{"total":28,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2502.09100","title":"Logical Reasoning in Large Language Models: A Survey","created":"2025-02-13","cited_by_count":55,"area":"lr"},{"id":"2503.15848","title":"Entropy-based Exploration Conduction for Multi-step Reasoning","created":"2025-03-20","cited_by_count":29,"area":"lr"},{"id":"2405.18711","title":"Calibrating Reasoning in Language Models with Internal Consistency","created":"2024-05-29","cited_by_count":28,"area":"lr"},{"id":"2507.09876","title":"ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models","created":"2025-07-14","cited_by_count":18,"area":"lr"},{"id":"2502.01477","title":"Achieving Time Series Reasoning Requires Rethinking Model Design, Tasks Formulation, and Evaluation","created":"2025-02-03","cited_by_count":17,"area":"lr"},{"id":"2602.09794","title":"Learning Global Hypothesis Space for Enhancing Synergistic Reasoning Chain","created":"2026-02-10","cited_by_count":17,"area":"lr"},{"id":"2410.23703","title":"OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models","created":"2024-10-31","cited_by_count":12,"area":"lr"},{"id":"2509.18639","title":"Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation","created":"2025-09-23","cited_by_count":11,"area":"lr"},{"id":"2602.07774","title":"GR2: Generative Reasoning Re-ranker","created":"2026-02-08","cited_by_count":11,"area":"lr"},{"id":"2512.19686","title":"Visual-Aware CoT: Achieving High-Fidelity Visual Consistency in Unified Models","created":"2025-12-22","cited_by_count":10,"area":"lr"},{"id":"2605.01194","title":"VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model","created":"2026-05-02","cited_by_count":9,"area":"lr"},{"id":"2410.24155","title":"Blind Spot Navigation in Large Language Model Reasoning with Thought Space Explorer","created":"2024-10-31","cited_by_count":7,"area":"lr"},{"id":"2511.17910","title":"L2V-CoT: Cross-Modal Transfer of Chain-of-Thought Reasoning via Latent Intervention","created":"2025-11-22","cited_by_count":5,"area":"lr"},{"id":"2510.01530","title":"LOGicalThought: Logic-Based Ontological Grounding of LLMs for High-Assurance Reasoning","created":"2025-10-02","cited_by_count":4,"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":"2511.02194","title":"Personalized Decision Modeling: Utility Optimization or Textualized-Symbolic Reasoning","created":"2025-11-04","cited_by_count":2,"area":"lr"},{"id":"2410.19221","title":"Can Stories Help LLMs Reason? Curating Information Space Through Narrative","created":"2024-10-25","cited_by_count":1,"area":"lr"},{"id":"2507.06999","title":"Learning Deliberately, Acting Intuitively: Unlocking Test-Time Reasoning in Multimodal LLMs","created":"2025-07-09","cited_by_count":1,"area":"lr"},{"id":"2509.21170","title":"Fine-Tuning LLMs to Analyze Multiple Dimensions of Code Review: A Maximum Entropy Regulated Long Chain-of-Thought Approach","created":"2025-09-25","cited_by_count":1,"area":"lr"},{"id":"2503.16304","title":"Bridging Technology and Humanities: Evaluating the Impact of Large Language Models on Social Sciences Research with DeepSeek-R1","created":"2025-03-20","cited_by_count":0,"area":"lr"},{"id":"2505.17481","title":"MARCO: Meta-Reflection with Cross-Referencing for Code Reasoning","created":"2025-05-23","cited_by_count":0,"area":"lr"},{"id":"2506.02726","title":"RACE-Align: Retrieval-Augmented and Chain-of-Thought Enhanced Preference Alignment for Large Language Models","created":"2025-06-03","cited_by_count":0,"area":"lr"},{"id":"2510.12067","title":"HiCoTraj:Zero-Shot Demographic Reasoning via Hierarchical Chain-of-Thought Prompting from Trajectory","created":"2025-10-14","cited_by_count":0,"area":"lr"},{"id":"2603.15397","title":"SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration","created":"2026-03-16","cited_by_count":0,"area":"lr"},{"id":"2604.17312","title":"A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions","created":"2026-04-19","cited_by_count":0,"area":"lr"},{"id":"2606.02054","title":"eMoT: evolving Memory-of-Thought via Symbolic Anchoring and Memory Corrosion","created":"2026-06-01","cited_by_count":0,"area":"lr"},{"id":"2607.14049","title":"Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models","created":"2026-07-15","cited_by_count":0,"area":"lr"}],"next_cursor":null}