reasoning-core/rc1
收藏Hugging Face2025-09-25 更新2025-11-01 收录
下载链接：
https://hf-mirror.com/datasets/reasoning-core/rc1
下载链接
链接失效反馈官方服务：
资源简介：
Reasoning Core是一个为大型语言模型（LLM）的符号推理训练设计的可验证奖励的强化学习环境（RLVR），专注于表达性符号任务，包括完整的谓词逻辑、带有TPTP的正式数学、新颖领域的正式规划以及语法任务等。
Reasoning Core is a Reinforcement Learning with Verifiable Rewards (RLVR) environment designed for symbolic reasoning training in Large Language Models (LLMs), focusing on expressive symbolic tasks such as full-fledged FOL, formal mathematics with TPTP, formal planning with novel domains, and syntax tasks.
提供机构：
reasoning-core
