#reasoning

开源推荐 None

GitHub 热门项目：Skywork-R1V

GitHub项目：Skywork-R1V 仓库地址：https://github。

Skywork multimodal and

2026-05-18 GitHub Trending

智能AI None

通过合规自我蒸馏降低法学硕士安全调整中的安全税

15239v1 Announce Type: new Abstract: Safety alignment often improves robustness to harmful queries at the cost of reason

safety and the

2026-05-18 Yu Fu, Longxuan Yu, Haz Sameen Shahgir, Zhipeng Wei, Hui Liu, N. Benjamin Erichson, Yue Dong

智能AI None

三思而后行：验证者引导的具体代理的行动选择

12620v1 Announce Type: new Abstract: Building generalist embodied agents capable of solving complex real-world tasks rem

the embodied agents

2026-05-14 Nishad Singhi, Christian Bialas, Snehal Jauhri, Vignesh Prasad, Georgia Chalvatzaki, Marcus Rohrbach, Anna Rohrbach

智能AI None

视觉语言模型是否在点击益智游戏中表现出类似人类的逻辑问题解决能力？

arXiv:2605.11223v1 Announce Type: new Abstract: Vision-Language(-Action) Models (VLMs) are increasingly applied to inter

and the reasoning

2026-05-13 Dominik Helfenstein, Marco Menner, Maximilian Triebel

开源推荐 None

GitHub 热门项目：DeepSeek-R1

GitHub项目：DeepSeek-R1 仓库地址：https://github。com/deepseek-ai/DeepSeek-R1 Stars：92005 | 作者：deepseek-ai 项目描述：暂无描述 ============

DeepSeek and reasoning

2026-05-13 GitHub Trending

智能AI None

递归推理系统的状态表示和终止

06690v1 Announce Type: new Abstract: Recursive reasoning systems alternate between acquiring new evidence and refining a

the and reasoning

2026-05-11 Debashis Guha, Amritendu Mukherjee, Sanjay Kukreja, Tarun Kumar

智能AI None

更多思考，更多偏差：推理模型中的长度驱动位置偏差

06672v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning and reasoning-tuned models such as DeepSeek-R1 are

reasoning and bias

2026-05-11 Xiao Wang

智能AI None

GraphDC：用于可扩展图算法推理的分而治之多智能体系统

06671v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated strong potential for many mathematic

and reasoning graph

2026-05-11 Wenjin Li, Jiaming Cui

智能AI None

财务文档问答的代理检索增强生成

arXiv:2605.05409v1 Announce Type: new Abstract: Financial document question answering (QA) demands complex multi-step nu

and reasoning that

2026-05-09 Yang Shu, Yingmin Liu, Zequn Xie

智能AI None

ZAYA1-8B技术报告

05365v1 Announce Type: new Abstract: We present ZAYA1-8B, a reasoning-focused mixture-of-experts (MoE) model with 700M a

and reasoning ZAYA

2026-05-09 Robert Washbourne, Rishi Iyer, Tomas Figliolia, Henry Zheng, Ryan Lorig-Roach, Sungyeon Yang, Pritish Yuvraj, Quentin Anthony, Yury Tokpanov, Xiao Yang, Ganesh Nanduru, Stephen Ebert, Praneeth Medepal

智能AI None

时间推理不是瓶颈：神经符号 QA 的概率不一致框架

04243v1 Announce Type: new Abstract: Despite significant advances, large language models (LLMs) continue to exhibit brit

reasoning the temporal

2026-05-08 Tran Quang Liem