#Agents

智能AI None

立场：人工智能推理代理之间的共谋风险证明了市场决策的认证要求是合理的

arXiv:2608.18078v1 Announce Type: new Abstract: This position paper argues that AI agents with chain-of-thought reasonin

agents that the

2026-08-20 Matthew Riemer, Tommaso Tosato, Amin Memarian, Maximilian Puelma Touzel, Glen Berseth, Irina Rish, Guillaume Dumas

智能AI None

内化未来：世界模型规划的统一代理训练范式

27483v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong capability in sequential

training and agents

2026-06-29 Xuan Zhang, Zhijian Zhou, Lingfeng Qiao, Yulei Qin, Ke Li, Xing Sun, Xiaoyu Tan, Chao Qu, Yuan Qi

安全攻防 None

监护代理：身份治理的下一层

AI agents are moving through enterprise environments, inheriting permissions, traversing systems, and executing decision

and are what

2026-06-26 info@thehackernews.com (The Hacker News)

开发者生态 None

AI编程代理拥有自己的Stack Overflow

Stack Overflow 宣布推出 Stack Overflow for Agents "。这是一个面向 AI 编程代理而非人类开发者的 API 优先型知识交流平台（目前处于测试阶段）。Stack Overflow 正试图弥合他们所谓的

Stack Overflow for

2026-06-25 作者：Matt Saunders

智能AI None

通过分类策略检索诊断和减轻代理说服中的复合失败

arXiv:2606.24976v1 Announce Type: new Abstract: Foundation-model agents in multi-step, open-ended environments frequentl

RAG from standard

2026-06-25 Pradyumna Narayana, Sana Ayromlou, Purvi Sehgal

安全攻防 None

阻止您的遗留基础设施劫持您的人工智能代理

Earlier this month, I spoke at the Gartner Security & Risk Management Summit about a blind spot most security programs a

security programs are

2026-06-22 info@thehackernews.com (The Hacker News)

智能AI None

YeasierAgent：代理社交沙盒作为意图驱动创建与平台无关的共生代理本机应用程序的画布

13722v1 Announce Type: new Abstract: This paper introduces YeasierAgent, an application-building paradigm based on symbi

and agents the

2026-06-15 Jory He

智能AI None

谷歌 DeepMind 担心当数百万智能体开始交互时会发生什么

Google DeepMind is funding research into the potential dangers of situations where millions of different AI agents inter

the research agents

2026-06-11 Will Douglas Heaven

智能AI None

人工智能代理可以综合科学结论吗？

11337v1 Announce Type: new Abstract: Scientific AI agents increasingly retrieve evidence, reason across sources, and syn

and that agents

2026-06-11 Hayoung Jung, Pedro Viana Diniz, Jos\'e Reinaldo Corr\^ea Roveda, Abner Fernandes da Silva, Haeun Jung, Enoch Tsai, Aleksandra Korolova, Manoel Horta Ribeiro

智能AI None

学习领导人类与人工智能混合型企业

As adoption of AI agents looks set to surge by as much as 300% in the next two years, leadership teams are carefully con

agents the are

2026-06-09 MIT Technology Review Insights

智能AI None

在神经科学数据到发现管道上评估人工智能代理的案例研究

arXiv:2606.07718v1 Announce Type: new Abstract: Agentic AI tools offer a promising path to automating software developme

and agents scientific

2026-06-09 Kai A. Horstmann, Ethan Lin, Alice A. Robie, Jennifer J. Sun, Kristin Branson

智能AI None

Syll：具有跨表面执行功能的开源个人自动化

arXiv:2606.07594v1 Announce Type: new Abstract: Personal AI agents must increasingly operate across APIs, shells, web su

and Syll agents

2026-06-09 Bo Zhang, Borui Zhang, Chenghao Jiang, Minglei Shi, Xiaofeng Wang, Zheng Zhu, Jie Zhou, Jiwen Lu

开源推荐 None

GitHub 热门项目：12 因子代理

GitHub项目：12-factor-agents 仓库地址：https://github。

the factor https

2026-05-29 GitHub Trending

智能AI None

Opus 4.8 刚发布，Redis 之父质疑跑分：DHH 盛赞的 GPT-5.5，正在动摇编码王座

5 月 28 日深夜，Anthropic 发布了其旗舰模型 Opus 的最新版本 Opus 4。7，这次升级的重点不只是模型跑分，而是围绕 Claude Code 增加了两个更直接面向开发者工作流的能力：dynamic workflows

Claude Opus dynamic

2026-05-29 Tina

数码硬件 None

正在为机器重建互联网

As AI agents move from experiments to production, AWS, Cloudflare, and others are redesigning cloud infrastructure for a

agents move from

2026-05-28 Rebecca Bellan

开发者生态 None

Show HN：Ktx – 数据代理的开源可执行上下文层

The context layer for data agents Quickstart · CLI Reference · Agent Setup · Slack ktx is a self-improving context layer

and ktx agents

2026-05-28 lucamrtl

社会热点 None

阿里 Qoder 推出 Cloud Agents，Agent 上线固件 1 天

IT之家 5 月 28 日消息，据阿里云消息，今天阿里 Qoder 上线全托管 AI Agent 运行平台 Cloud Agents，可提供 Agent 底座、模型服务及运行环境等全栈 Agent 能力，企业可通过 API 的方式直接调用，

Agent Qoder Cloud

2026-05-28 IT之家

智能AI None

异构仿真环境中联合强化学习的个性化观察归一化

arXiv:2605.27385v1 Announce Type: new Abstract: Federated reinforcement learning (FedRL) enables multiple agents to coll

agents and FedRL

2026-05-28 Yiran Pang, Zhen Ni, Xiangnan Zhong

智能AI None

DynaSchedBench：基于 LLM 的调度代理中校准的动态调度基准和可观测性悖论

arXiv:2605.27566v1 Announce Type: new Abstract: Progress in neural combinatorial optimization for Dynamic Flexible Job S

for agents and

2026-05-28 Shijie Cao, Yuan Yuan, Jing Liu

开源推荐 None

GitHub 热门项目：compose

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

composio https Composio

2026-05-27 GitHub Trending