🤖 AI Agent 研究Research
【arXiv】随着代理处理更长、更复杂的问题，控制执行本身就成为一项任务。运行中的每一步都会带来新的控制选择，例如在哪些部分工作的基础上进行，是否重新开始，或何时停止。我们介绍
【arXiv】As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control choices, like which partial work to build on, whether to start fresh, or when to stop. We introduce
【arXiv】客服代表的表现取决于推理能力和行动环境。我们研究AI-for-AI的测试时间，询问构建器如何在两个模型的权重保持不变的情况下学习为目标构建更好的执行环境。
【arXiv】Agent performance depends on both reasoning ability and the environment in which it acts. We study test-time AI-for-AI, asking how a Builder can learn to construct better execution environments for a Target while both models' weights remain fixed. To
借鉴法学硕士代理的经验已成为培养不断学习和扩展自身能力的自我发展代理的关键范例。在这种范式中，合成座席技能已成为将积累的经验转化为可重用的程序知识的有前途的解决方案，成为在运行时提供座席的线束系统的重要层。
Learning from experience in LLM agents has become a key paradigm for developing self-evolving agents that continuously learn and expand their capabilities. Within this paradigm, synthesizing the agent skill has emerged as a promising solution for transforming accumulated experience into reusable procedural knowledge, serving as an important layer for the harness system that supplies agents at runtime.
多个代理通常可能在组织中发生冲突：例如，一个编码代理更改存储库中的接口，但另一个编码代理在旧版本上继续开发，现有测试变得过时。我们引入了Relic ，它将反复出现的协作故障转化为组织拥有的可执行协议。
Multiple agents may often conflict in an organization: for example, one coding agent changes an interface in a repository, but another continues to develop on the old version where existing tests become stale. We introduce Relic, which turns recurring collaboration failures into organization-owned, executable protocols.
⭐ GitHub 热门项目GitHub Trending
【GitHub】任何您想要的缺口。只需询问您的经纪人即可。Claude Code和Codex从普通文件重建的可破解MacBook缺口。开源。（⭐ 2 ）
【GitHub】Any notch you want. Just ask your agent. A hackable MacBook notch that Claude Code and Codex rebuild from plain files. Open source. （⭐ 2）
【GitHub】适用于muse.ai个人AI代理的高性能OpenAI兼容API网关和网桥，为9Router多模型集成做好准备。（⭐ 53 ）
【GitHub】High-performance OpenAI-compatible API gateway and bridge for muse.ai personal AI agents, ready for 9Router multi-model integration. （⭐ 53）
【GitHub】为您的人工智能代理刹车：每个工具调用都会根据您的规则进行检查，在风险时等待人工批准，并记录在可以篡改的审计跟踪中。适用于Claude Code和任何MCP应用程序。（⭐ 4 ）
【GitHub】Brakes for your AI agents: every tool call is checked against your rules, held for human approval when risky, and recorded in a tamper-evident audit trail. Works with Claude Code and any MCP app. （⭐ 4）
【GitHub】您的编码代理编写视频。由您导演。Claude Code/Codex视频的本地开源Premiere风格编辑器。（⭐ 1 ）
【GitHub】Your coding agent writes the video. You direct it. A local, open-source Premiere-style editor for Claude Code / Codex videos. （⭐ 1）
【GitHub】开源MCP服务器，让Claude Code、Codex、Gemini CLI或Cursor将iOS订阅应用程序从IDEA运送到TestFlight （⭐ 2 ）
【GitHub】Open-source MCP server that lets Claude Code, Codex, Gemini CLI or Cursor ship an iOS subscription app from idea to TestFlight （⭐ 2）
🚀 模型与行业动态Models & Industry
为了国家安全，得知America.gov没有产生幻觉，以至于它正在写冗长的诗歌，这是一种解脱。
For the sake of national security, it's a relief to learn that America.gov is not hallucinating to the point that it's penning lengthy poetry.
在OpenAI周二推出新的人工智能代理Dots之前， Elon Musk的xAI已经获得了域名“dot.com” ，该域名现在重定向到Grok聊天机器人下载页面。
Before OpenAI launched its new AI agent, Dots, on Tuesday, Elon Musk's xAI had already acquired the domain name "dot.com," which now redirects to the Grok chatbot download page.
OpenAI正在构建传统应用商店模式的替代方案，将ChatGPT转变为人们和人工智能代理都可以发现和使用软件的地方。
OpenAI is building out the pieces of an alternative to the traditional app store model, turning ChatGPT into a place where software can be discovered and used by people and AI agents alike.
预计新一轮融资将是该公司在2027年推迟公开亮相之前的最后一轮融资。
The new round is anticipated to be the company's last before its delayed 2027 public debut.
据TechCrunch了解， OpenAI并不是英伟达开放代理安全平台的公共支持者，但它正在与英伟达私下合作。
OpenAI isn't a public supporter of Nvidia's Open Agent Safety Platform, but it is privately working with Nvidia, TechCrunch has learned.
🔥 社区热议Community
【Lobsters】热度: 17↑ | 8 评论 | 标签: vibecoding
【Lobsters】热度: 17↑ | 8 评论 | 标签: vibecoding
【HN】热度: 792 分 | 734 评论
【HN】热度: 792 分 | 734 评论
【HN】热度: 408 分 | 130 评论
【HN】热度: 408 分 | 130 评论
【HN】热度: 26 分 | 0 评论
【HN】热度: 26 分 | 0 评论