{"total":46,"rows":[{"id":"2411.15124","title":"Tulu 3: Pushing Frontiers in Open Language Model Post-Training","created":"2024-11-22","cited_by_count":1053,"area":"lr"},{"id":"2505.20347","title":"SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data","created":"2025-05-25","cited_by_count":51,"area":"lr"},{"id":"2503.03686","title":"MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems","created":"2025-03-05","cited_by_count":50,"area":"lr"},{"id":"2503.18866","title":"Reasoning to Learn from Latent Thoughts","created":"2025-03-24","cited_by_count":45,"area":"lr"},{"id":"2505.20161","title":"Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning","created":"2025-05-26","cited_by_count":40,"area":"lr"},{"id":"2407.21009","title":"AI-Assisted Generation of Difficult Math Questions","created":"2024-07-30","cited_by_count":37,"area":"lr"},{"id":"2504.13941","title":"Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning","created":"2025-04-15","cited_by_count":31,"area":"lr"},{"id":"2503.02324","title":"PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Models","created":"2025-03-04","cited_by_count":22,"area":"lr"},{"id":"2503.07018","title":"Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoning","created":"2025-03-10","cited_by_count":21,"area":"lr"},{"id":"2410.03864","title":"DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search","created":"2024-10-04","cited_by_count":17,"area":"lr"},{"id":"2410.12881","title":"MIND: Math Informed syNthetic Dialogues for Pretraining LLMs","created":"2024-10-15","cited_by_count":14,"area":"lr"},{"id":"2503.13447","title":"MetaScale: Test-Time Scaling with Evolving Meta-Thoughts","created":"2025-03-17","cited_by_count":13,"area":"lr"},{"id":"2601.21459","title":"HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing","created":"2026-01-29","cited_by_count":10,"area":"lr"},{"id":"2505.07313","title":"Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study","created":"2025-05-12","cited_by_count":8,"area":"lr"},{"id":"2508.18255","title":"Hermes 4 Technical Report","created":"2025-08-25","cited_by_count":8,"area":"lr"},{"id":"2410.01504","title":"PersonaMath: Boosting Mathematical Reasoning via Persona-Driven Data Augmentation","created":"2024-10-02","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":"2508.06533","title":"The Art of Breaking Words: Rethinking Multilingual Tokenizer Design","created":"2025-08-03","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":"2510.09905","title":"The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMs","created":"2025-10-10","cited_by_count":6,"area":"lr"},{"id":"2505.14147","title":"SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning","created":"2025-05-20","cited_by_count":5,"area":"lr"},{"id":"2507.20984","title":"SmallThinker: A Family of Efficient Large Language Models Natively Trained for Local Deployment","created":"2025-07-28","cited_by_count":5,"area":"lr"},{"id":"2510.09275","title":"Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation","created":"2025-10-10","cited_by_count":5,"area":"lr"},{"id":"2506.13065","title":"MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"id":"2509.20553","title":"Perspectra: Choosing Your Experts Enhances Critical Thinking in Multi-Agent Research Ideation","created":"2025-09-24","cited_by_count":4,"area":"lr"},{"id":"2512.06867","title":"Do Persona-Infused LLMs Affect Performance in a Strategic Reasoning Game?","created":"2025-12-07","cited_by_count":4,"area":"lr"},{"id":"2510.23544","title":"LimRank: Less is More for Reasoning-Intensive Information Reranking","created":"2025-10-27","cited_by_count":3,"area":"lr"},{"id":"2602.08167","title":"Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2603.06595","title":"Rethinking Personalization in Large Language Models at the Token Level","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2509.18864","title":"Conf-Profile: A Confidence-Driven Reasoning Paradigm for Label-Free User Profiling","created":"2025-09-23","cited_by_count":2,"area":"lr"},{"id":"2511.07397","title":"Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents","created":"2025-11-10","cited_by_count":2,"area":"lr"},{"id":"2607.15277","title":"Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models","created":"2026-07-16","cited_by_count":2,"area":"lr"},{"id":"2505.19848","title":"Improving Multilingual Math Reasoning for African Languages","created":"2025-05-26","cited_by_count":1,"area":"lr"},{"id":"2603.18361","title":"Synthetic Data Generation for Training Diversified Commonsense Reasoning Models","created":"2026-03-18","cited_by_count":1,"area":"lr"},{"id":"2606.00869","title":"Enhancing LLM Metacognition via Cognitive Pairwise Training","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2606.12730","title":"Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior","created":"2026-06-10","cited_by_count":1,"area":"lr"},{"id":"2502.18452","title":"FRIDA to the Rescue! Analyzing Synthetic Data Effectiveness in Object-Based Common Sense Reasoning for Disaster Response","created":"2025-02-25","cited_by_count":0,"area":"lr"},{"id":"2508.13654","title":"Input-Time Scaling: Adding Noise and Irrelevance into Less-Is-More Drastically Improves Reasoning Performance and Efficiency","created":"2025-08-19","cited_by_count":0,"area":"lr"},{"id":"2510.10528","title":"Merlin's Whisper: Enabling Efficient Reasoning in Large Language Models via Black-box Persuasive Prompting","created":"2025-10-12","cited_by_count":0,"area":"lr"},{"id":"2601.03940","title":"Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs","created":"2026-01-07","cited_by_count":0,"area":"lr"},{"id":"2601.08679","title":"PersonaDual: Balancing Personalization and Objectivity via Adaptive Reasoning","created":"2026-01-13","cited_by_count":0,"area":"lr"},{"id":"2603.05120","title":"Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning","created":"2026-03-05","cited_by_count":0,"area":"lr"},{"id":"2604.02794","title":"CharTool: Tool-Integrated Visual Reasoning for Chart Understanding","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2605.07699","title":"DRIP-R: A Benchmark for Decision-Making and Reasoning Under Real-World Policy Ambiguity in the Retail Domain","created":"2026-05-08","cited_by_count":0,"area":"lr"},{"id":"2607.28648","title":"Why It Hurts: Identifying the Drivers of Negative Thoughts in Emotional Support Conversations","created":"2026-06-02","cited_by_count":0,"area":"lr"},{"id":"2609.00014","title":"Behaviorally Grounded User Profiles from the Wild for Personalized Alignment and Multi-Perspective Reasoning","created":"2026-08-11","cited_by_count":0,"area":"lr"}],"next_cursor":null}