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。

2025-10-29 至 2025-10-29 共收录 6 篇信号源：cs.CL, cs.AI, cs.LG

1. 数学推理 6 篇

2504.11364 2025-10-29 cs.LG cs.AI cs.CL 85%

Offline Learning and Forgetting for Reasoning with Large Language Models

Tianwei Ni, Allen Nie, Sapana Chaudhary, Yao Liu, Huzefa Rangwala, Rasool Fakoor

机构 * Mila - Quebec AI Institute & Université de Montréal（魁北克AI研究所与蒙特利尔大学）； Amazon Web Services（亚马逊网络服务）

专题命中数学推理：reasoning(title,abstract)；CoT(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Published in Transactions on Machine Learning Research (TMLR), 2025. Code: https://github.com/twni2016/llm-reasoning-uft

2510.23629 2025-10-29 cs.LG cs.AI cs.PL 84%

Chain of Execution Supervision Promotes General Reasoning in Large Language Models

Nuo Chen, Zehua Li, Keqin Bao, Junyang Lin, Dayiheng Liu

机构 * Qwen Team, Alibaba（阿里巴巴通义实验室）； Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； University of Science and Technology of China（中国科学技术大学）

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

Journal ref 39th Conference on Neural Information Processing Systems (NeurIPS 2025)

2510.24397 2025-10-29 cs.AI 70%

APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training

Jiarui Qin, Yunjia Xi, Junjie Huang, Renting Rui, Di Yin, Weiwen Liu, Yong Yu, Weinan Zhang, Xing Sun

机构 * Tencent Youtu Lab（腾讯优图实验室）； Shanghai Jiao Tong University（上海交通大学）

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

Comments 46 pages

2505.10978 2025-10-29 cs.LG cs.AI 62%

Group-in-Group Policy Optimization for LLM Agent Training

Lang Feng, Zhenghai Xue, Tingcong Liu, Bo An

机构 * Nanyang Technological University（南洋理工大学）； Skywork AI

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

Comments NeurIPS 2025

2506.00799 2025-10-29 cs.LG 57%

Uni-LoRA: One Vector is All You Need

Kaiyang Li, Shaobo Han, Qing Su, Wei Li, Zhipeng Cai, Shihao Ji

机构 * School of Computing University of Connecticut（计算机学院美国康涅狄格大学）； NEC Labs America（NEC美国实验室）； Dept. of Computer Science Georgia State University（计算机科学系美国佐治亚州立大学）

专题命中数学推理：reasoning(abstract)；分类 cs.LG

Comments NeurIPS 2025 Spotlight

2510.23818 2025-10-29 cs.LG 57%

ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning

Yilang Zhang, Xiaodong Yang, Yiwei Cai, Georgios B. Giannakis

机构 * ML Research, Morgan Stanley, New York, NY 10019, USA（ML研究，摩根大通，纽约，纽约州，10019，美国）； Visa Research, Austin, TX 78759, USA（Visa研究，奥斯汀，德克萨斯州，78759，美国）； Department of ECE, University of Minnesota, MN 55455, USA（电子工程系，明尼苏达大学，明尼苏达州，55455，美国）

专题命中数学推理：reasoning(abstract)；分类 cs.LG