{"total":15,"rows":[{"id":"2508.11408","title":"On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting","created":"2025-08-15","cited_by_count":91,"area":"lr"},{"id":"2508.20722","title":"rStar2-Agent: Agentic Reasoning Technical Report","created":"2025-08-28","cited_by_count":54,"area":"lr"},{"id":"2510.03222","title":"Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward","created":"2025-10-03","cited_by_count":25,"area":"lr"},{"id":"2603.22117","title":"On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation","created":"2026-03-23","cited_by_count":13,"area":"lr"},{"id":"2508.09883","title":"Beyond Scaling Law: A Data-Efficient Distillation Framework for Reasoning","created":"2025-08-13","cited_by_count":11,"area":"lr"},{"id":"2510.00237","title":"Debunk the Myth of SFT Generalization","created":"2025-09-30","cited_by_count":8,"area":"lr"},{"id":"2510.05132","title":"Training Large Language Models To Reason In Parallel With Global Forking Tokens","created":"2025-10-01","cited_by_count":6,"area":"lr"},{"id":"2510.13166","title":"CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning","created":"2025-10-15","cited_by_count":5,"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":"2603.10359","title":"HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation","created":"2026-03-11","cited_by_count":3,"area":"lr"},{"id":"2605.05826","title":"AGPO: Asymmetric Group Policy Optimization for Verifiable Reasoning and Search Ads Relevance at JD","created":"2026-05-07","cited_by_count":2,"area":"lr"},{"id":"2602.02160","title":"D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use","created":"2026-02-02","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":"2609.21247","title":"When Does Reasoning Help in Machine Translation? A Hierarchical Analysis of LRM Reasoning Traces","created":"2026-09-18","cited_by_count":0,"area":"lr"},{"id":"2609.35699","title":"Distillation Defenses Easily Break After Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}