#And

开源推荐 None

GitHub 热门项目：HRM

GitHub项目：HRM 仓库地址：https://github。

and HRM https

2026-05-22 GitHub Trending

安全攻防 None

CISA 将利用的 Langflow 和 Trend Micro Apex One 漏洞添加到 KEV 中

The U.S. Cybersecurity and Infrastructure Security Agency (CISA) on Thursday added two security flaws impacting Langflow

The and Langflow

2026-05-22 info@thehackernews.com (The Hacker News)

开源推荐 None

GitHub 热门项目：zeroclaw

GitHub项目：zeroclaw 仓库地址：https://github。

zeroclaw the and

2026-05-22 GitHub Trending

开发者生态 None

休眠 TUI HTTP 客户端

Introduction Slumber is a terminal-based HTTP client, built for interacting with REST and other HTTP clients。It has two

and the Slumber

2026-05-22 jicea

开发者生态 None

CODA：将 Transformer 块重写为 GEMM-Epilogue 程序

Computer Science > Machine Learning arXiv:2605。

Transformer GEMM and

2026-05-22 matt_d

开发者生态 None

Google Workspace 促销代码：5 月份 14% 折扣

Boost your productivity and save with exclusive Google Workspace coupons from WIRED。Get up to 14% off plans for three mo

and Boost your

2026-05-22 Jacob Roach

开源推荐 None

GitHub 热门项目：llm-answer-engine

GitHub项目：llm-answer-engine 仓库地址：https://github。

https and com

2026-05-22 GitHub Trending

开发者生态 None

显示 HN：Claude 代码的规范驱动开发工作流程

Spec Driven Development approach allows to squeeze more from coding agents thanks to few strong concepts: - decompositio

you and specs

2026-05-22 sermakarevich

开发者生态 None

随着人工智能利润飙升，三星芯片工人平均将获得 34 万美元奖金

【HN用户评论摘要】 Meanwhile tech workers in the US spend all day online defending billionaires who wouldn't piss on them to put

workers blah and

2026-05-22 carabiner

开发者生态 None

是时候建立一个新的互联网了

It is time to build a new internet 22 May, 2026 Every morning that we open our phones and laptops, we are staring pitifu

and the are

2026-05-22 mrmarket

开源推荐 None

GitHub 热门项目：fullmoon-ios

GitHub项目：fullmoon-ios 仓库地址：https://github。

fullmoon https app

2026-05-22 GitHub Trending

开发者生态 None

IBM 化的谷歌？

Google is Shattering Under Its Own Weight (The IBM-ification of Google。) 21 May, 2026 I used to think Google owning the

the Google and

2026-05-22 sabatonfan

智能AI None

AgentAtlas：LLM 代理的超越结果排行榜

arXiv:2605.20530v1 Announce Type: new Abstract: Large language model agents now act on codebases, browsers, operating sy

the model and

2026-05-22 Parsa Mazaheri, Kasra Mazaheri

智能AI None

用于衡量前沿人工智能能力的开放世界评估

20520v1 Announce Type: new Abstract: Benchmark-based evaluation remains important for tracking frontier AI progress。

and for evaluations

2026-05-22 Sayash Kapoor, Peter Kirgis, Andrew Schwartz, Stephan Rabanser, J. J. Allaire, Rishi Bommasani, Harry Coppock, Magda Dubois, Gillian K Hadfield, Andrew B. Hall, Sara Hooker, Seth Lazar, Steve Newman,

智能AI None

$ECUAS_n$：用于对不确定性增强系统进行原则评估的一系列指标

arXiv:2605.20490v2 Announce Type: new Abstract: In high-stakes automated decision-making, access to predictive uncertain

the and uncertainty

2026-05-22 Lautaro Estienne, Erik Ernst, Mat\'ias Vera, Pablo Piantanida, Luciana Ferrer

智能AI None

用于 Horn 逻辑推理的高质量嵌入

20467v1 Announce Type: new Abstract: Neural networks can be trained to rank the choices made by logical reasoners, resul

and embeddings examples

2026-05-22 Yifan Zhang, Yasir White, Dean Clark, Joseph Sanchez, Jevon Lipsey, Ashely Hirst, Jeff Heflin

智能AI None

AgentCo-op：基于检索的可互操作多代理工作流的综合

arXiv:2605.20425v1 Announce Type: new Abstract: Designing multi-agent workflows is especially difficult in open-ended sc

and agents workflows

2026-05-22 Shuaike Shen, Wenduo Cheng, Shike Wang, Mingqian Ma, Jian Ma

智能AI None

OSCToM：强化学习引导的高阶心理理论对抗生成

20423v1 Announce Type: new Abstract: Large Language Models (LLMs) perform well on many language tasks, but their Theory

the and OSCToM

2026-05-22 Sharmin Sultana Srishty, Kazi Mahathir Rahman, Malaika Parizat Sakkhi, Samia Shahid Prianna, Shaikhul Islam Sinat

智能AI None

用于闭环优化、仿真和建模编排的工具增强代理

arXiv:2605.20190v1 Announce Type: new Abstract: Iterative industrial design-simulation optimization is bottlenecked by t

and CAD CAE

2026-05-22 Liyuan Deng, Shujian Deng, Yongkang Chen, Yongkang Dai, Zhihang Zhong, Linyang Li, Xiao Sun, Yilei Shi, Huaxi Huang

智能AI None

SOLAR：一种自我优化的开放式自主代理，用于终身学习和持续适应

arXiv:2605.20189v1 Announce Type: new Abstract: Despite the remarkable success of large language models (LLMs), they sti

the adaptation and

2026-05-22 Nitin Vetcha, Dianbo Liu