{"total":40,"rows":[{"id":"2501.12599","title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","created":"2025-01-22","cited_by_count":1210,"area":"lr"},{"id":"2406.08464","title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","created":"2024-06-12","cited_by_count":346,"area":"lr"},{"id":"2404.02078","title":"Advancing LLM Reasoning Generalists with Preference Trees","created":"2024-04-02","cited_by_count":192,"area":"lr"},{"id":"2503.04472","title":"DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models","created":"2025-03-06","cited_by_count":158,"area":"lr"},{"id":"2407.13690","title":"DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving","created":"2024-06-18","cited_by_count":95,"area":"lr"},{"id":"2502.02384","title":"STAIR: Improving Safety Alignment with Introspective Reasoning","created":"2025-02-04","cited_by_count":77,"area":"lr"},{"id":"2505.22375","title":"Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition","created":"2025-05-28","cited_by_count":62,"area":"lr"},{"id":"2504.10081","title":"RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability","created":"2025-04-14","cited_by_count":59,"area":"lr"},{"id":"2507.23751","title":"CoT-Self-Instruct: Building high-quality synthetic prompts for reasoning and non-reasoning tasks","created":"2025-07-31","cited_by_count":32,"area":"lr"},{"id":"2402.08259","title":"A Survey of Table Reasoning with Large Language Models","created":"2024-02-13","cited_by_count":29,"area":"lr"},{"id":"2406.17271","title":"DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph","created":"2024-06-25","cited_by_count":26,"area":"lr"},{"id":"2411.07681","title":"What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?","created":"2024-11-12","cited_by_count":23,"area":"lr"},{"id":"2410.09335","title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need","created":"2024-10-12","cited_by_count":22,"area":"lr"},{"id":"2501.09213","title":"FineMedLM-o1: Enhancing Medical Knowledge Reasoning Ability of LLM from Supervised Fine-Tuning to Test-Time Training","created":"2025-01-16","cited_by_count":19,"area":"lr"},{"id":"2508.12680","title":"Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation","created":"2025-08-18","cited_by_count":13,"area":"lr"},{"id":"2406.14115","title":"Take the essence and discard the dross: A Rethinking on Data Selection for Fine-Tuning Large Language Models","created":"2024-06-20","cited_by_count":12,"area":"lr"},{"id":"2501.11877","title":"From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning","created":"2025-01-21","cited_by_count":12,"area":"lr"},{"id":"2506.02096","title":"SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis","created":"2025-06-02","cited_by_count":12,"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":"2504.10766","title":"How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients","created":"2025-04-14","cited_by_count":8,"area":"lr"},{"id":"2506.06998","title":"What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding","created":"2025-06-08","cited_by_count":8,"area":"lr"},{"id":"2505.17266","title":"Select2Reason: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning","created":"2025-05-22","cited_by_count":7,"area":"lr"},{"id":"2410.04407","title":"Lens: Rethinking Multilingual Enhancement for Large Language Models","created":"2024-10-06","cited_by_count":6,"area":"lr"},{"id":"2505.09118","title":"Seeing Beyond the Scene: Enhancing Vision-Language Models with Interactional Reasoning","created":"2025-05-14","cited_by_count":4,"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":"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":"2505.11628","title":"Critique-Guided Distillation for Robust Reasoning via Refinement","created":"2025-05-16","cited_by_count":2,"area":"lr"},{"id":"2511.15958","title":"JudgeBoard: Benchmarking and Enhancing Small Language Models for Reasoning Evaluation","created":"2025-11-20","cited_by_count":2,"area":"lr"},{"id":"2605.17003","title":"Learning-Zone Energy: Online Data Selection for Efficient RL Post-Training","created":"2026-05-16","cited_by_count":2,"area":"lr"},{"id":"2505.17082","title":"GemMaroc: Unlocking Darija Proficiency in LLMs with Minimal Data","created":"2025-05-20","cited_by_count":1,"area":"lr"},{"id":"2602.01884","title":"Entropy-Guided Data-Efficient Training for Multimodal Reasoning Reward Models","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2608.00181","title":"Cross-Benchmark Generalization in Long-Horizon Agents","created":"2026-07-31","cited_by_count":1,"area":"lr"},{"id":"2609.39183","title":"Aligning Thoughts with Answers: Probability Rewards to Tame Thinking Drift","created":"2026-09-30","cited_by_count":1,"area":"lr"},{"id":"2507.02173","title":"Data Diversification Methods In Alignment Enhance Math Performance In LLMs","created":"2025-07-02","cited_by_count":0,"area":"lr"},{"id":"2508.18673","title":"Tailored Teaching with Balanced Difficulty: Elevating Reasoning in Multimodal Chain-of-Thought via Prompt Curriculum","created":"2025-08-26","cited_by_count":0,"area":"lr"},{"id":"2602.23632","title":"MMKG-RDS: Reasoning Data Synthesis via Deep Mining of Multimodal Knowledge Graphs","created":"2026-02-27","cited_by_count":0,"area":"lr"},{"id":"2609.33780","title":"Selecting Diverse SFT Traces Improves Post-RL Generalization","created":"2026-09-27","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":"2610.13285","title":"BoundaryEvo: Data-Model Co-Evolution at the Capability Boundary for Long-Chain Reasoning Distillation","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.16104","title":"SelectTTRL: Representation-Guided Data Selection for Efficient Test-Time Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"lr"}],"next_cursor":null}