🤖 AI Agent 研究Research
【arXiv】基于大型语言模型的多Agent系统正在从固定的交互拓扑演变为动态编排的Agent Swarms。但是，现有的基准仍然主要基于单代理或通用代理任务，因此
【arXiv】Large language model-based multi-agent systems are evolving from fixed interaction topologies toward dynamically orchestrated Agent Swarms. However, existing benchmarks are still largely based on single-agent or general-purpose agent tasks, making it
【arXiv】大型语言模型（ LLM ）越来越多地用于软件开发，但其在复杂硬件设计中的使用仍然有限。这一差距源于公共硬件培训数据的稀缺性和根本不同的方法
【arXiv】Large language models (LLMs) are increasingly used in software development, but their use in complex hardware design remains limited. This gap stems from both the scarcity of public hardware training data and the fundamentally different methodologies
LLM代理越来越多地在运行时修改自己的提示、工具、中间件、资源和执行利用。这种自我进化可以提高能力，但成功的突变可能会留下持续的影响，这种影响在与产生它的状态不同的状态下无法安全逆转。
LLM agents increasingly modify their own prompts, tools, middleware, resources, and execution harnesses at runtime. Such self-evolution can improve capability, but a successful mutation may leave persistent effects that cannot be safely reversed in states different from the one in which it was created.
生成模型可以将自然语言提示转化为图像、文本、代码和其他内容，从而降低制作草稿和组件的成本。本调查研究代理人工制品创建，我们将其定义为有状态构建，其中人工智能系统实质上构建或修改可交付成果，中间观测重定向后来的工作。
Generative models can turn natural-language prompts into images, text, code, and other content, lowering the cost of producing drafts and components. This survey examines agentic artifact creation, which we define as stateful construction in which an AI system materially constructs or revises a deliverable and intermediate observations redirect later work.
⭐ GitHub 热门项目GitHub Trending
【GitHub】Claude Code和Codex的开源投资研究技能（⭐ 1 ）
【GitHub】Open-source investment research skills for Claude Code and Codex （⭐ 1）. gaedsstudio/YouRich.
【GitHub】将任何AI特工变成AI科学家。全球19万多名科学家使用的排名第一的科学代理技能库。165项随时可用的经验证的技能，以及100多个涵盖生物学、化学和我的科学数据库（⭐ 60 ）
【GitHub】Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, me （⭐ 60）
【GitHub】轻量级的Wayland脚手架，用于AI代理在不窃取人类主机焦点、光标、工作区或剪贴板的情况下操作一个GUI应用程序。（⭐ 5 ）
【GitHub】Lightweight Wayland scaffold for AI agents to operate one GUI app without stealing the human's host focus, cursor, workspace, or clipboard. （⭐ 5）
【GitHub】Claude Code、Cowork和Chat的开源技能—编码、商业和日常生活（⭐ 0 ）
【GitHub】Open-source skills for Claude Code, Cowork, and Chat — coding, business, and everyday life （⭐ 0）
【GitHub】适用于专业护理机构的开源Claude Code技能包— PDPM、NTA捕获、MDS合规性、付款人合同、事先授权、调查就绪性、人口普查分析。由Magicare (magicare.ai)提供。（⭐ 1 ）
【GitHub】Open-source Claude Code skill packs for skilled nursing facilities — PDPM, NTA capture, MDS compliance, payer contracts, prior auth, survey readiness, census analytics. By Magicare (magicare.ai). （⭐ 1）
🚀 模型与行业动态Models & Industry
苹果公司表示，有证据表明，一名前员工在得知自己正在接受调查后，销毁了数据被盗的证据。
Apple says it has evidence that a former employee destroyed evidence of data theft after learning he was under investigation.
OpenAI的ChatGPT和SpaceXAI的Grok版本将加入谷歌的Gemini ，成为五角大楼人工智能工具的中央门户。
Versions of OpenAI's ChatGPT and SpaceXAI's Grok will join Google's Gemini on the Pentagon's central portal for AI tools.
随着对人工智能影响者的沮丧情绪不断增长， Instagram正在限制未公开的人工智能个人资料的覆盖范围。
As frustration over AI influencers has been growing, Instagram is limiting the reach of undisclosed AI profiles.
Blue Voice接受了有关部门特定法律、地方条例、协议和准则的培训，通用人工智能工具无法在公共互联网上访问这些法律、条例、协议和准则。
Blue Voice is trained on department-specific laws, local ordinances, protocols, and guidelines that general-purpose AI tools can't access on the public internet.
这家成立三年的初创公司表示，它在ARR和盈利能力方面达到了$ 1500万，然后筹集了最新的$ 1500万。
The three-year-old startup says it reached $15 million in ARR and profitability before raising its latest $15 million round.
🔥 社区热议Community
【Lobsters】热度: 52↑ | 36 评论 | 标签: satire, vibecoding
【Lobsters】热度: 52↑ | 36 评论 | 标签: satire, vibecoding
【Lobsters】热度: 76↑ | 29 评论 | 标签: rant, vibecoding
【Lobsters】热度: 76↑ | 29 评论 | 标签: rant, vibecoding
【HN】热度: 294 分 | 346 评论
【HN】热度: 294 分 | 346 评论