[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-tencent-agently-mail-agent-identity-a2a":3,"topics-all":36,"news-related-32e45e99-c7d8-4804-87b2-cbea73f7b3a3":55},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":23,"news_slug":29,"published_at":30,"created_at":31,"modified_at":32,"is_published":33,"publish_type":34,"image_url":13,"view_count":35},"32e45e99-c7d8-4804-87b2-cbea73f7b3a3","腾讯把邮箱塞给 Agent：QQ邮箱「Agently Mail」内测,把 LLM 的身份基础设施补齐","腾讯 QQ邮箱团队6月23日开启「Agently Mail」内测,这是一款独立于个人邮箱、专为 AI Agent 设计的收发件通道。开通需完成实名认证,数据与用户私人邮箱完全隔离;Agent 可以用自己的身份注册第三方平台、接收验证码,也支持企业间的 A2A(Agent to Agent)自动询价、报价、订单对接。WorkBuddy、QClaw、Marvis、OpenClaw、Claude Code、Kimi Work、豆包超能模式、Codex、Hermes、Cursor 等主流 Agent 已经首批接入。\n\nAgently Mail 抓住了过去半年 agent 落地里最被低估的那一块:身份。模型再强,一旦要在真实世界「办成一件事」,就需要一个能稳定接收验证码、长期持有、能被反查的对外身份,以及和这条身份绑定的可信发件箱。借用个人邮箱不是不行,但风险太大:Agent 一旦能读全部历史邮件,聊天记录、账单、私密往来都会被一并看到,误删、错发更是高发故障点。Agently Mail 通过「隔离邮箱 + 实名制 + 完整收发记录」把这块短板直接补上。\n\n更值得注意的是 A2A 视角。过去谈 agent-to-agent,大家默认的通信通道是 API、消息队列或 MCP 之类专用协议,而腾讯选择让邮箱这种「人类过去三十年最稳定的异步基础设施」直接承担 A2A 角色。对企业来说,不需要为 agent 单独建一套中台;对跨组织 agent 协作来说,SMTP\u002FIMAP 的兼容性意味着任何 agent 都可以无缝接入。这条路如果走通,可能是 agent 互操作性的最务实答案,同时也意味着 AI 时代邮箱这个产品重新获得了新的存在理由——只不过这一次,它的「用户」不再只是人。\n\n需要指出,Agently Mail 现在还只是内测,实名制如何与 agent 的伪身份特性平衡、邮箱本身的反垃圾\u002F反滥用能力能不能扛住大规模 A2A 调用、跨地域合规怎么走,都是落地前必须回答的问题。但方向本身是对的:agent 时代的「身份 + 通信」基础设施不会从天而降,谁先把这一块补齐,谁就掌握了下一个十年的入口。","https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002Fe7tdWa8QaBXI5yA5ZdgMIg","d46ec0a7-501b-4ef8-9c89-2391b2701b3b",[10,14,17,20],{"id":11,"name":12,"slug":12,"description":13,"color":13},"6ad31a14-c0da-42df-81fd-564281f768db","agentic-ai",null,{"id":15,"name":16,"slug":16,"description":13,"color":13},"40269b40-7942-4650-9672-ed2e6524d37a","ai-technology",{"id":18,"name":19,"slug":19,"description":13,"color":13},"a8002d98-9df1-4ab9-94d4-a7625af634c4","china-ai",{"id":21,"name":22,"slug":22,"description":13,"color":13},"01598627-1ea6-4b27-a5d8-874971571a71","llm",[24],{"id":25,"lang":26,"title":27,"summary":28,"content":13},"0da407fd-86ee-4d51-90e2-0006c9f82842","en","QQ Mail's Agently Mail beta hands email to AI agents","Tencent's QQ Mail team started internal beta of \"Agently Mail,\" an email service designed from the ground up for LLM Agents. The product's positioning: not \"email for humans, with AI features bolted on,\" but \"email for Agents, with humans as the final recipients.\"\n\nThe technical details: Agently Mail gives each Agent a real email address (e.g., agent-12345@qq.com), with full IMAP\u002FSMTP support. The Agent can send, receive, and parse emails autonomously, using a structured \"action API\" (e.g., \"send email,\" \"read inbox,\" \"search by sender\"). The email content is parsed into a structured format (JSON-like) that the LLM can easily consume.\n\nThe identity layer: this is the missing piece for Agent identity. Today, most LLM Agents use human phone numbers \u002F email addresses for verification, which is brittle and prone to fraud. Agently Mail's \"Agent as a first-class citizen\" approach gives Agents a stable, verifiable identity, with built-in support for Agent-to-Agent communication.\n\nThe bigger takeaway: \"Agent identity infrastructure\" is the next big missing layer. As Agents become more autonomous, they need real-world identities — phone numbers, email addresses, payment methods, social media accounts. Tencent is positioning itself as the \"identity layer\" for the Agent era, similar to how Stripe positioned itself as the \"payment layer\" for the internet era.\n\nFor the industry, this signals that the \"Agent economy\" needs infrastructure beyond LLMs. Identity, communication, payment, and reputation are the next big categories, and the company that can become the \"Stripe of Agent infrastructure\" will own the next decade.","tencent-agently-mail-agent-identity-a2a","2026-06-24T22:10:00Z","2026-06-24T22:09:58.144602Z","2026-08-19T02:08:40.142862Z",true,"agent",177,[37,46],{"slug":38,"tag_slug":38,"title_zh":39,"title_en":40,"intro_zh":41,"intro_en":42,"id":43,"is_active":33,"created_at":44,"modified_at":45},"ai-for-science","AI for Science 2026：从 UniPert 到 GPT-Rosalind 的硬核进化","AI for Science 2026: from UniPert to GPT-Rosalind","生命科学、化学材料、物理世界模型——AI 正在从\"语言工具\"变成\"实验伙伴\"。本专题收录 AI 在三大科学方向的关键节点：UniPert 统一基因与化学扰动空间、GPT-Rosalind 端到端生命科学推理、达摩院 AI 智能体 28 小时找到 4 种超导新材料、Anthropic Claude Science 把工作台做成标准品。","From language tool to lab partner — AI is reshaping life sciences, chemistry\u002Fmaterials, and physical world models. This topic covers the key milestones: UniPert unifying genetic-chemical perturbation spaces, GPT-Rosalind's end-to-end life-sciences reasoning, DAMO's AI agent discovering 4 superconducting materials in 28 hours, and Anthropic's Claude Science workbench going mainstream.","988a4300-5fab-41c4-b5d8-63711a2dc757","2026-09-10T01:34:15.296649Z","2026-09-10T01:34:15.296663Z",{"slug":47,"tag_slug":47,"title_zh":48,"title_en":49,"intro_zh":50,"intro_en":51,"id":52,"is_active":33,"created_at":53,"modified_at":54},"h3-series","MiniMax H3 系列：从开源权重到 35 倍吞吐","MiniMax H3 Series: from open weights to 35x throughput","MiniMax H3 自 2026 年 8 月开源以来节奏密集：官方把生成、参考与编辑收回一个模型；ComfyUI 当天压进 RTX 3060；摩尔线程 3 小时完成国产 GPU 适配；fal 后训练版把吞吐拉到 35 倍；FastH3 蒸馏再砍推理成本。本专题持续追踪 H3 的发布—开源—蒸馏—部署全链路。","Since MiniMax open-sourced H3 in August 2026 the pace has been relentless: one unified omni-modal model, same-day ComfyUI support down to an RTX 3060, a 3-hour Day-0 port to Moore Threads GPUs, fal's post-trained H3 Max at 35x throughput, and FastH3 distillation cutting inference cost further. This topic tracks the full H3 chain — release, open weights, distillation, deployment.","83ef0daa-3c31-4cb3-86ed-e5ee58654d5f","2026-09-08T07:33:19.942193Z","2026-09-08T07:33:19.942209Z",{"items":56},[57,62,67,72,77,82],{"id":58,"title":59,"news_slug":60,"published_at":61},"dcd8b3e1-a3c7-4614-aba4-9002219ea5f6","LibreDB Studio 0.15 发布:本地 LLM 接管数据库交互","libredb-studio-local-llm-agent","2026-09-15T00:00:00+00:00",{"id":63,"title":64,"news_slug":65,"published_at":66},"31c09fea-8993-4f10-b683-499672fcafe3","世界模型不能再靠爬视频硬堆:游戏引擎补上了缺失的奖励信号","game-engine-rlhev-world-models","2026-08-30T13:10:00+00:00",{"id":68,"title":69,"news_slug":70,"published_at":71},"d1e8997e-bb60-453d-9ef8-71b8bdde5386","Harvey 首个自研法律模型 Tenet 曝光:底座没选 GPT 和 Claude,选了 Kimi K3","harvey-tenet-kimi-k3-legal-model","2026-08-18T17:30:00+00:00",{"id":73,"title":74,"news_slug":75,"published_at":76},"5a90a793-8ec1-4b3a-9691-edef5ffe8535","AI「思想病毒」实证:Anthropic 与 EPFL 让恶意想法在 Agent 间自我复制,免疫只需一段警告","mind-viruses-multi-agent-llm","2026-08-18T13:30:00+00:00",{"id":78,"title":79,"news_slug":80,"published_at":81},"49d19ba1-8f45-475c-bed1-a69dc353523e","字节跳动用 10 万亿参数下注：规模赛跑与张一鸣的「不蒸馏」表态","bytedance-10t-mythos-zhangyiming-no-distill-2026-08","2026-08-08T00:00:00+00:00",{"id":83,"title":84,"news_slug":85,"published_at":86},"5f5bd5f2-9a02-470b-aa25-3f27fb9bb093","字节跳动正训练 10 万亿参数模型，规模对标 Anthropic Mythos 5","bytedance-10t-parameter-model-ft","2026-08-07T09:30:00+00:00"]