meituan-longcat/R-HORIZON-Math500
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-Math500
下载链接
链接失效反馈官方服务：
资源简介：
R-HORIZON是一个旨在通过查询组合来激发大型推理模型（LRMs）的长时推理行为的新方法。它将孤立的问题转化为复杂的多步推理场景，揭示了即使是最高级的LRMs在面临跨越长时间推理范围的相关问题时，也会出现显著的性能下降。R-HORIZON基准测试包括来自数学、代码生成和代理应用等领域的6个代表性数据集。
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, revealing that even the most advanced LRMs suffer significant performance degradation when facing interdependent problems that span long reasoning horizons. The R-HORIZON benchmark includes 6 representative datasets from mathematics, code generation, and agent applications.
提供机构：
meituan-longcat
