{"total":30,"rows":[{"id":"2601.20802","title":"Reinforcement Learning via Self-Distillation","created":"2026-01-28","cited_by_count":332,"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":"2602.04118","title":"Learning to Reason in 13 Parameters","created":"2026-02-04","cited_by_count":14,"area":"lr"},{"id":"2604.06628","title":"Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability","created":"2026-04-08","cited_by_count":14,"area":"lr"},{"id":"2601.14249","title":"Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment","created":"2026-01-20","cited_by_count":13,"area":"lr"},{"id":"2601.16547","title":"CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation","created":"2026-01-23","cited_by_count":11,"area":"lr"},{"id":"2602.01058","title":"Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning","created":"2026-02-01","cited_by_count":11,"area":"lr"},{"id":"2602.02301","title":"Advancing General-Purpose Reasoning Models with Modular Gradient Surgery","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2604.01499","title":"Matching Accuracy, Different Geometry: Evolution Strategies vs GRPO in LLM Post-Training","created":"2026-04-02","cited_by_count":8,"area":"lr"},{"id":"2604.14164","title":"How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data","created":"2026-03-23","cited_by_count":8,"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":"2602.14147","title":"LaViDa-R1: Advancing Reasoning for Unified Multimodal Diffusion Language Models","created":"2026-02-15","cited_by_count":7,"area":"lr"},{"id":"2605.09725","title":"On-Policy Distillation with Best-of-N Teacher Rollout Selection","created":"2026-05-10","cited_by_count":7,"area":"lr"},{"id":"2602.13407","title":"On-Policy Supervised Fine-Tuning for Efficient Reasoning","created":"2026-02-13","cited_by_count":4,"area":"lr"},{"id":"2605.07505","title":"LiteGUI: Lightweight GUI Agents via Multi-Solution Guided Distillation and Dual-Level Reinforcement Learning","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"id":"2603.01683","title":"Surgical Post-Training: Proximal On-Policy Distillation for Reasoning with Knowledge Retention","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2606.02398","title":"A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL","created":"2026-06-01","cited_by_count":3,"area":"lr"},{"id":"2601.08274","title":"Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees","created":"2026-01-13","cited_by_count":2,"area":"lr"},{"id":"2601.09233","title":"GIFT: Reconciling Post-Training Objectives via Variational Finite-Temperature Gibbs Initialization","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2605.28008","title":"Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training","created":"2026-05-27","cited_by_count":2,"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":"2602.10006","title":"Answer First, Reason Later: Aligning Search Relevance via Mode-Balanced Reinforcement Learning","created":"2026-02-10","cited_by_count":0,"area":"lr"},{"id":"2605.18903","title":"Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era","created":"2026-05-17","cited_by_count":0,"area":"lr"},{"id":"2608.13698","title":"GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings","created":"2026-08-13","cited_by_count":0,"area":"lr"},{"id":"2609.22194","title":"A Pinch of SFT, A Dash of RL: When Reinforcement Learning Helps Long-Horizon Advertising Agents","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2610.04158","title":"How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.05200","title":"Learning without Overwriting: A Theory of Self-Distillation and Supervised Fine-Tuning in Continual Reasoning","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.06671","title":"Learning What to Imitate: Entropy-Aware Distribution Mixing","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.17726","title":"TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"id":"2610.19687","title":"Function-Space Temporal Self-Distillation for Policy Optimization","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}