{"total":22,"rows":[{"id":"2507.16812","title":"MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning","created":"2025-07-22","cited_by_count":59,"area":"lr"},{"id":"2510.01624","title":"Quagmires in SFT-RL Post-Training: When High SFT Scores Mislead and What to Use Instead","created":"2025-10-02","cited_by_count":28,"area":"lr"},{"id":"2508.05618","title":"Learning to Reason for Factuality","created":"2025-08-07","cited_by_count":24,"area":"lr"},{"id":"2601.09088","title":"Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning","created":"2026-01-14","cited_by_count":17,"area":"lr"},{"id":"2508.17784","title":"Proximal Supervised Fine-Tuning","created":"2025-08-25","cited_by_count":16,"area":"lr"},{"id":"2510.01539","title":"Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code","created":"2025-10-02","cited_by_count":10,"area":"lr"},{"id":"2605.19433","title":"Backtracking When It Strays: Mitigating Dual Exposure Biases in LLM Reasoning Distillation","created":"2026-05-19","cited_by_count":8,"area":"lr"},{"id":"2602.14763","title":"Unlocking Reasoning Capability on Machine Translation in Large Language Models","created":"2026-02-16","cited_by_count":6,"area":"lr"},{"id":"2603.02091","title":"Learning from Synthetic Data Improves Multi-hop Reasoning","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2512.21002","title":"Distilling the Essence: Efficient Reasoning Distillation via Sequence Truncation","created":"2025-12-24","cited_by_count":5,"area":"lr"},{"id":"2601.10109","title":"Skill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation","created":"2026-01-15","cited_by_count":5,"area":"lr"},{"id":"2603.21289","title":"When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning","created":"2026-03-22","cited_by_count":5,"area":"lr"},{"id":"2510.24794","title":"MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models","created":"2025-10-27","cited_by_count":4,"area":"lr"},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2512.13279","title":"AIR: Post-training Data Selection for Reasoning via Attention Head Influence","created":"2025-12-15","cited_by_count":3,"area":"lr"},{"id":"2603.00296","title":"Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning","created":"2026-02-27","cited_by_count":3,"area":"lr"},{"id":"2509.15661","title":"SightSound-R1: Cross-Modal Reasoning Distillation from Vision to Audio Language Models","created":"2025-09-19","cited_by_count":1,"area":"lr"},{"id":"2605.13165","title":"STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2602.22508","title":"Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering","created":"2026-02-26","cited_by_count":0,"area":"lr"},{"id":"2605.02290","title":"Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding","created":"2026-05-04","cited_by_count":0,"area":"lr"},{"id":"2605.20201","title":"Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning","created":"2026-04-06","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"}],"next_cursor":null}