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。

2025-10-22 至 2025-10-22 共收录 2 篇信号源：cs.CL, cs.AI, cs.LG

1. 测试时计算 2 篇

2510.12838 2025-10-22 cs.CL cs.AI 84%

A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning

Qianben Chen, Jingyi Cao, Jiayu Zhang, Tianrui Qin, Xiaowan Li, King Zhu, Dingfeng Shi, He Zhu, Minghao Liu, Xiaobo Liang, Xin Gui, Ge Zhang, Jian Yang, Yuchen Eleanor Jiang, Wangchunshu Zhou

专题命中测试时计算：reasoning(title,abstract)；chain-of-thought(abstract)；分类 cs.CL、cs.AI

Comments 12 pages, 6 figures

2509.05542 2025-10-22 cs.LG 57%

DreamPRM-1.5: Unlocking the Potential of Each Instance for Multimodal Process Reward Model Training

Qi Cao, Pengtao Xie

机构 * University of California, San Diego（加州大学圣地亚哥分校）

专题命中测试时计算：reasoning(abstract)；分类 cs.LG