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。

2025-08-28 至 2025-08-28 共收录 4 篇信号源：cs.CL, cs.AI, cs.LG

1. 复杂问题求解 4 篇

2508.19277 2025-08-28 cs.LG cs.AI cs.CR 79%

POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization

Xinyu Li, Tianjin Huang, Ronghui Mu, Xiaowei Huang, Gaojie Jin

专题命中复杂问题求解：reasoning(abstract)；chain-of-thought(abstract)；CoT(abstract)；分类 cs.AI、cs.LG

2508.19870 2025-08-28 cs.NI 50%

Secure Multi-LLM Agentic AI and Agentification for Edge General Intelligence by Zero-Trust: A Survey

Yinqiu Liu, Ruichen Zhang, Haoxiang Luo, Yijing Lin, Geng Sun, Dusit Niyato, Hongyang Du, Zehui Xiong, Yonggang Wen, Abbas Jamalipour, Dong In Kim, Ping Zhang

专题命中复杂问题求解：reasoning(abstract)

Comments 35 pages

2508.19800 2025-08-28 q-bio.TO q-bio.BM 50%

A Multi-Layered Framework for Modeling Human Biology: From Basic AI Agents to a Full-Body AI Agent

Aoqi Wang, Jiajia Liu, Jianguo Wen, Yangyang Luo, Zhiwei Fan, Liren Yang, Xi Hu, Ruihan Luo, Yankai Yu, Sophia Li, Weiling Zhao, Xiaobo Zhou

专题命中复杂问题求解：reasoning(abstract)

2508.16652 2025-08-28 cs.CV 50%

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability

Ashwath Vaithinathan Aravindan, Abha Jha, Mihir Kulkarni

机构 * University of Southern California（南加州大学）

专题命中复杂问题求解：reasoning(abstract)

Comments To be published in Explainable Computer Vision: Quo Vadis? workshop at ICCV'25