[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"news-slug-google-io-2026-antigravity-2-0-orchestration":3,"topics-all":33,"news-related-fcd676ca-d64a-4321-b453-45763c803a67":52},{"id":4,"title":5,"summary":6,"content":6,"original_url":7,"source_id":8,"tags":9,"translations":20,"news_slug":26,"published_at":27,"created_at":28,"modified_at":29,"is_published":30,"publish_type":31,"image_url":13,"view_count":32},"fcd676ca-d64a-4321-b453-45763c803a67","Google I\u002FO 2026 重新定义AI开发：Antigravity 2.0 将多智能体编排带入产品级工程","今年 Google I\u002FO 的主角不是某个新模型，而是开发栈本身的一次彻底重构。Google Antigravity 2.0 从一个 AI 辅助 IDE 演变为完整的 agent-first 开发平台，覆盖 CLI、SDK、托管执行环境和企业部署，形成了一个从本地到云端的统一 agent 编排体系。\n\n核心变化在于抽象层的升级：以往 AI 辅助工具仍以单次调用为核心，但 Antigravity 2.0 将多智能体协作提升为主要开发原语。动态子智能体支持并行工作流、定时任务实现后台自动化、持久化隔离环境让多轮对话状态无缝保留——这些能力将 agent 从\"对话工具\"转变为\"可编程的自动化基础设施\"。\n\nManaged Agents API 是最值得关注的产品里程碑：一条 API 调用即可在隔离 Linux 容器中启动完整 agent 实例，由 Gemini 3.5 Flash 提供底层推理能力。这意味着企业开发者不再需要手动管理 agent 状态环境，基础设施层已被 Google 抽象掉。benchmark 数据也印证了这个方向——3.5 Flash 跑分超越 3.1 Pro，吞吐量是其他前沿模型的 4 倍，并行智能体调用时延迟不再成为瓶颈。\n\n从落地案例看，企业已在用这套体系重构工作流：Shopify 并行运行数据分析师子智能体、Macquarie Bank 推理百页复杂文档、Ramp 做多模态票据理解，均依赖 3.5 Flash 在长时序多步任务中的稳定表现。\n\n更重要的是，Google 已将 Gemini CLI 完全迁移至 Antigravity CLI，原有 Agent Skills、Hooks、Subagents 全部保留，Extensions 更名为 Plugins。这是一个明确的信号：Google 正在将 agent 工作流确立为继微服务之后的下一个主流开发范式，Antigravity 2.0 是工具层的锚点。\n\n对开发者而言，2026 年 AI 开发的新起点已不再是\"写好 prompt\"，而是\"设计好 agent 协作拓扑\"。理解这套体系的价值，比又追一个新模型发布更有长期意义。","https:\u002F\u002Fdevelopers.googleblog.com\u002Fall-the-news-from-the-google-io-2026-developer-keynote\u002F","3318cb52-f01e-4c9e-a34a-5dbc9fa986f2",[10,14,17],{"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},"8cf7490f-2449-4ba7-be19-61befa0d92b4","google",{"id":18,"name":19,"slug":19,"description":13,"color":13},"0a93ec8e-ea39-4693-81de-563ca8c173f7","inference",[21],{"id":22,"lang":23,"title":24,"summary":25,"content":13},"6bf50ce6-861a-4a2b-ba7a-232824aab5e1","en","Google I\u002FO 2026: Antigravity 2.0 goes product-grade multi-agent","Google's I\u002FO 2026 developer keynote announced Antigravity 2.0, the next generation of the multi-Agent orchestration platform. The new version brings product-level engineering features: collaboration between Agents, version control of Agent workflows, and integration with Google's cloud infrastructure.","google-io-2026-antigravity-2-0-orchestration","2026-05-28T05:00:00Z","2026-05-28T13:07:50.388716Z","2026-08-19T02:08:40.142862Z",true,"agent",252,[34,43],{"slug":35,"tag_slug":35,"title_zh":36,"title_en":37,"intro_zh":38,"intro_en":39,"id":40,"is_active":30,"created_at":41,"modified_at":42},"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":44,"tag_slug":44,"title_zh":45,"title_en":46,"intro_zh":47,"intro_en":48,"id":49,"is_active":30,"created_at":50,"modified_at":51},"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":53},[54,59,64,69,74,79],{"id":55,"title":56,"news_slug":57,"published_at":58},"a3e9cf60-e2dc-4ac6-a1a6-1089ee721bc9","Google Antigravity CLI 全面开放：子Agent并行编排进入终端开发时代","google-antigravity-cli-sub-agent-parallel","2026-05-31T10:05:00+00:00",{"id":60,"title":61,"news_slug":62,"published_at":63},"a4f1f3a9-2900-4ed0-9dff-016535a6f707","Google I\u002FO 推出 Managed Agents API：一条调用完成Agent部署，代价是放弃执行层控制","google-managed-agents-api-one-call","2026-05-25T04:10:00+00:00",{"id":65,"title":66,"news_slug":67,"published_at":68},"af34b075-9fd7-4f0f-8f87-eb947fd81f4e","Dream-RSI:Google 让智能体在历史里做梦,发现调用省 162 倍","dream-rsi-replay-simulator","2026-09-15T23:20:00+00:00",{"id":70,"title":71,"news_slug":72,"published_at":73},"20568e5d-3b66-495d-8b7b-0a702f3c7877","模型在进化,训练环境却是死的:Google 开源 EnvHarness,给环境也套一层 harness","google-envharness-agent-environments","2026-08-20T10:42:06+00:00",{"id":75,"title":76,"news_slug":77,"published_at":78},"36055e5f-136f-497d-8763-3ed6609f59ff","Meta Muse Glimmer 30B 本地落地:Apache 2.0 的开源智能体,把 Agent 装进 24GB 显存","meta-muse-glimmer-30b-local-agent-apache2-r2","2026-08-19T03:00:00+00:00",{"id":80,"title":81,"news_slug":82,"published_at":83},"7d371b09-9792-465d-b73a-3d0af4735129","InferenceBench：15 个前沿 Agent 自主做 LLM 推理优化","inferencebench-open-ended-llm-optimization","2026-08-16T12:00:00+00:00"]