meituan-longcat/R-HORIZON-AIME24
收藏Hugging Face2025-10-21 更新2025-10-25 收录
下载链接：
https://hf-mirror.com/datasets/meituan-longcat/R-HORIZON-AIME24
下载链接
链接失效反馈官方服务：
资源简介：
R-HORIZON是一种新的方法，旨在通过查询组合来刺激大型推理模型（LRMs）中的长时推理行为。它将孤立的问题转化为复杂的多步推理场景，并建立了R-HORIZON基准，该基准由数学、代码生成和代理应用领域的6个代表性数据集组成。R-HORIZON还允许使用长时推理数据来启用强化学习与验证奖励（RLVR）。
R-HORIZON is a novel method designed to stimulate long-horizon reasoning behaviors in Large Reasoning Models (LRMs) through query composition. It transforms isolated problems into complex multi-step reasoning scenarios, establishing the R-HORIZON Benchmark comprising 6 representative datasets from mathematics, code generation, and agent applications. R-HORIZON enables reinforcement learning with verified rewards (RLVR) using long-horizon reasoning data.
提供机构：
meituan-longcat
