{"total":24,"rows":[{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820,"area":"lr"},{"id":"2310.10631","title":"Llemma: An Open Language Model For Mathematics","created":"2023-10-16","cited_by_count":388,"area":"lr"},{"id":"2405.20304","title":"Group Robust Preference Optimization in Reward-free RLHF","created":"2024-05-30","cited_by_count":95,"area":"lr"},{"id":"2602.05547","title":"Multi-Task GRPO: Reliable LLM Reasoning Across Tasks","created":"2026-02-05","cited_by_count":14,"area":"lr"},{"id":"2510.12225","title":"HoneyBee: Data Recipes for Vision-Language Reasoners","created":"2025-10-14","cited_by_count":13,"area":"lr"},{"id":"2503.10061","title":"Compute Optimal Scaling of Skills: Knowledge vs Reasoning","created":"2025-03-13","cited_by_count":11,"area":"lr"},{"id":"2510.26122","title":"Reasoning Path Divergence: A New Metric and Curation Strategy to Unlock LLM Diverse Thinking","created":"2025-10-30","cited_by_count":10,"area":"lr"},{"id":"2505.22308","title":"Transformers Pretrained on Procedural Data Contain Modular Structures for Algorithmic Reasoning","created":"2025-05-28","cited_by_count":9,"area":"lr"},{"id":"2508.15202","title":"Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models","created":"2025-08-21","cited_by_count":7,"area":"lr"},{"id":"2506.08672","title":"RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling","created":"2025-06-10","cited_by_count":6,"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":"2505.07293","title":"AttentionInfluence: Adopting Attention Head Influence for Weak-to-Strong Pretraining Data Selection","created":"2025-05-12","cited_by_count":5,"area":"lr"},{"id":"2510.03605","title":"Understanding the Role of Training Data in Test-Time Scaling","created":"2025-10-04","cited_by_count":4,"area":"lr"},{"id":"2510.12157","title":"Self-Verifying Reflection Helps Transformers with CoT Reasoning","created":"2025-10-14","cited_by_count":4,"area":"lr"},{"id":"2606.21090","title":"Self-Improvement Can Self-Regress: The Rise-and-Collapse Failure Mode of LLM Self-Training","created":"2026-06-17","cited_by_count":4,"area":"lr"},{"id":"2509.25531","title":"MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2512.24503","title":"Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice","created":"2025-12-30","cited_by_count":3,"area":"lr"},{"id":"2603.01293","title":"Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models","created":"2026-03-01","cited_by_count":3,"area":"lr"},{"id":"2605.05227","title":"Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods","created":"2026-04-19","cited_by_count":3,"area":"lr"},{"id":"2505.21598","title":"Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives","created":"2025-05-27","cited_by_count":2,"area":"lr"},{"id":"2404.01135","title":"Enhancing Reasoning Capacity of SLM using Cognitive Enhancement","created":"2024-04-01","cited_by_count":1,"area":"lr"},{"id":"2509.05542","title":"DreamPRM-1.5: Unlocking the Potential of Each Instance for Multimodal Process Reward Model Training","created":"2025-09-05","cited_by_count":1,"area":"lr"},{"id":"2510.05133","title":"Characterizing Model Behavior Under Synthetic Data Training: An Empirical Study Across Scales and Mixing Ratios","created":"2025-10-01","cited_by_count":0,"area":"lr"},{"id":"2609.36535","title":"When Updating Stops Being Learning: Rethinking LLM Self-Evolution via learnable information gain","created":"2026-09-29","cited_by_count":0,"area":"lr"}],"next_cursor":null}