arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

大模型推理能力

大模型数学、逻辑、规划、多步推理和测试时计算能力。

2025-08-01 至 2025-08-01 共收录 4 信号源:cs.CL, cs.AI, cs.LG

1. 数学推理 4 篇

2507.22928 2025-08-01 cs.CL cs.AI 90%

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding

Xi Chen, Aske Plaat, Niki van Stein

专题命中 数学推理 :reasoning(title,abstract);chain-of-thought(title,abstract);CoT(abstract);分类 cs.CL、cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.23317 2025-08-01 cs.LG 83%

Good Learners Think Their Thinking: Generative PRM Makes Large Reasoning Model More Efficient Math Learner

Tao He, Rongchuan Mu, Lizi Liao, Yixin Cao, Ming Liu, Bing Qin

专题命中 数学推理 :reasoning(title,abstract);math reasoning(abstract);分类 cs.LG

Comments 33 pages, 3 figures, 19 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.22958 2025-08-01 cs.CV cs.AI cs.LG 62%

CHECK-MAT: Checking Hand-Written Mathematical Answers for the Russian Unified State Exam

Ruslan Khrulev

机构 * Moscow State University(莫斯科国立大学)

专题命中 数学推理 :reasoning(abstract);分类 cs.AI、cs.LG

Comments 15 pages, 3 figures, 10 tables. Code is available at: https://github.com/Karifannaa/Auto-check-EGE-math

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.23407 2025-08-01 cs.CL 57%

Beyond Passive Critical Thinking: Fostering Proactive Questioning to Enhance Human-AI Collaboration

Ante Wang, Yujie Lin, Jingyao Liu, Suhang Wu, Hao Liu, Xinyan Xiao, Jinsong Su

机构 * School of Informatics, Xiamen University, China(厦门大学信息学院) Department of Digital Media Technology, Xiamen University, China(厦门大学数字媒体技术系) Baidu Inc., Beijing, China(百度公司)

专题命中 数学推理 :reasoning(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏