内容来源：https://blog.google/products-and-platforms/products/chrome/gemini-3-auto-browse/

内容总结：

谷歌Chrome浏览器迎来AI助手Gemini深度整合，开启“智能浏览”新时代

谷歌近日宣布，为其Chrome浏览器（适用于MacOS、Windows和Chromebook Plus设备）推出基于最新Gemini 3模型的重大AI功能更新。此次升级旨在将Chrome从一款工具转变为理解用户需求的“智能伙伴”，通过一系列创新功能显著提升网络浏览与多任务处理效率。

核心更新亮点如下：

1. 常驻侧边栏助手：全新的侧边栏体验让Gemini助手常驻浏览器旁。用户可在主标签页工作的同时，利用侧边栏并行处理其他任务，例如快速对比多标签页信息、总结不同网站的产品评测、或在复杂日程中安排活动时间，实现高效无干扰的多任务操作。

2. 内置创意图像工具：创意工具Nano Banana被直接集成至Chrome中。用户无需下载或切换标签页，即可在浏览网页时直接对图像进行实时编辑与风格转换，例如为客厅 redesign 获取灵感，或将研究数据转化为信息图，极大简化了创作流程。

3. 深度联动谷歌应用：Gemini现与Gmail、日历、YouTube、地图、购物及航班等谷歌核心应用深度打通。例如，在规划差旅时，它能自动提取邮件中的会议详情，结合航班信息提供推荐方案，并协助起草行程通知邮件，形成流畅的跨应用工作流。

4. 即将推出个性化智能：未来数月，已在Gemini应用中广受好评的“个性化智能”功能将登陆Chrome。该功能在用户授权下，可基于过往互动提供高度个性化的网页搜索答案与建议，使浏览体验更贴合个人需求。

5. 自动浏览处理复杂任务：面向美国AI Pro和Ultra订阅用户推出的“自动浏览”功能，能代表用户自动完成多步骤的线上操作。它可协助完成诸如比价预订酒店机票、填写在线表格、整理税务文件、管理订阅续费等繁琐事务，甚至在规划主题派对时，能识别图片元素并自动搜索、比价、添加符合预算的装饰品至购物车。

6. 安全与可控性保障：所有新功能均以安全为设计核心，配备了全新的防护措施。特别是“自动浏览”在执行敏感操作（如支付或发帖）前会主动暂停并请求用户确认，确保用户始终掌控最终决策。

此外，Chrome将支持谷歌与Shopify、Etsy等行业领导者共同制定的全新开放标准——通用商务协议，旨在为AI代理在浏览器内代表用户进行商务操作提供无缝、安全的支持。

此次更新标志着Chrome正式迈向“智能代理浏览”的新阶段，通过深度整合Gemini的AI能力，致力于将用户从日常网络琐事中解放出来，更专注于创意与核心工作。

中文翻译：

浏览新时代：在Chrome中启用Gemini

我们为MacOS、Windows和Chromebook Plus平台的Chrome浏览器推出了Gemini的重大更新，助您充分挖掘网络潜能。基于我们最智能的模型Gemini 3，我们在Chrome中集成了强大的全新AI功能，通过全新的侧边栏体验，帮助您高效处理多任务。我们还与最受欢迎的Google应用进行了深度整合，让您在处理复杂的多步骤工作流程时更高效——借助自动浏览功能，您能轻松应对繁琐操作；而在未来几个月，个性化智能功能将为您提供更贴合情境的个性化帮助。全新的Chrome版Gemini就像一位得力助手，让您在网络上查找信息和完成任务变得前所未有的轻松。

推出侧边栏浏览新方式：重新构想多任务处理

我们推出了全新的侧边栏体验，让Chrome版Gemini用户无论身处哪个标签页，都能随时获得浏览助手。这有助于您节省时间，无中断地处理多任务。您可以保持主工作标签页开启，同时使用侧边栏处理另一项任务。我们的测试人员已将其用于各种场景：在众多标签页间对比选项、汇总不同网站的产品评价，甚至在最混乱的日程表中为活动安排时间。

Chrome版Gemini现可在侧边栏中开启，多任务处理更轻松。

通过Nano Banana即时转换网页图像

我们还将Nano Banana的创意功能直接引入Chrome，让您无需下载、重新上传图像或打开新标签页，即可实时转换图像。所有Chrome版Gemini用户均可使用此功能，只需在侧边栏输入提示词说明您的意图。无论是获取客厅改造的创意灵感，还是将研究数据转化为精美的信息图，它都能助您一臂之力。

无需复制粘贴或重新上传；Chrome版Gemini使用Nano Banana在当前浏览器窗口中转换图像。

在关联应用中高效完成任务

Chrome版Gemini支持关联应用，例如与Gmail、日历、YouTube、地图、Google购物和Google航班等应用的集成。这些深度整合帮助您快速完成任务。例如，如果您要前往参加会议并需要预订航班，Gemini可以找出包含活动详情的旧邮件，参考Google航班的上下文提供建议，随后还能起草邮件告知同事您的抵达时间。这些功能可在Gemini设置的“关联应用”部分启用。

Chrome版Gemini可与其他Google应用（如Gmail）协同工作。

个性化智能：更贴心、更主动的Chrome

用户已发现Gemini应用中的个性化智能功能非常实用，未来几个月我们将其引入Chrome。借助个性化智能，您始终掌控一切。您可以选择启用，并随时决定是否连接或断开您的应用。

Chrome将记住过往对话的上下文，因此无论您在网络上寻找什么，都能获得量身定制的答案；您还可以为Gemini添加特定指令，以获得更个性化的回复。Chrome中的个性化智能将浏览体验从一个通用工具转变为理解您、提供相关、主动且情境感知帮助的可靠伙伴。

让Chrome自动浏览为您代劳，节省时间

多年来，Chrome自动填充功能一直处理着琐碎事务，例如自动填写地址或信用卡信息，助您更快完成任务。如今，Chrome更进一步，不仅能处理简单任务，还能协助完成智能代理操作，让您将复杂的旅行安排或专业工作流程交由它处理。对于美国的AI Pro和Ultra订阅用户，我们推出了Chrome自动浏览2——一种强大的智能代理体验，可代您处理多步骤的繁琐任务。

自动浏览能通过处理一些繁琐工作来优化您的假期规划，例如研究不同日期组合的酒店和航班费用，助您找到预算友好的出行时间。我们的测试人员已将其用于各种事务：预约安排、填写繁琐的在线表格、收集税务文件、获取水管工和电工报价、检查账单支付状态、提交费用报告、管理订阅以及加速更新驾照——节省了大量时间。

您也可以用它处理更复杂的任务：假设您正在策划一场千禧年主题派对，并从一张完美捕捉时代精神的照片中获得灵感。自动浏览凭借Gemini 3的多模态能力，可以识别图片内容，搜索类似物品并将其加入购物车——同时控制预算，甚至自动应用折扣码。如果您授予自动浏览权限，它还可以使用Google密码管理器来处理需要登录的任务。

理解您的创意构想后，Chrome版Gemini可帮您查找非常具体的派对装饰品并加入购物车。

具备全新智能代理能力（自动浏览）的Chrome版Gemini可为您填写表格，例如使用PDF中的信息。

Chrome版Gemini可根据您对酒店和航班的要求，为您推荐最佳住宿周末。

Chrome版Gemini可帮您找到合适的公寓，并根据您的条件筛选结果。

最后，Chrome将支持Google通用商务协议（UCP），这是一个与Shopify、Etsy、Wayfair和Target等行业领导者共同开发的全新开放标准，用于智能代理商务。这一新开放标准确保AI代理能在Chrome中无缝代表用户执行操作。

安全与控制，设计为本

我们以严格的安全标准构建了Chrome版Gemini，并引入了全新的防护措施，帮助您抵御新型网络威胁。为了增强控制力，自动浏览功能在设计上会暂停并明确请求您确认，或提示您完成某些任务（如进行购买或在社交媒体上发布内容）。

自动浏览功能旨在让您全程知晓，并请求确认敏感操作。

我们才刚刚开始探索智能代理网络的潜力，迫不及待想看到这些新功能如何帮助您在Chrome中保持灵感，完成更多工作。

英文来源：

The new era of browsing: Putting Gemini to work in Chrome
We’re introducing major updates to Gemini in Chrome 1 for MacOS, Windows and Chromebook Plus that help you get the most out of the web. Built on Gemini 3, our most intelligent model, we’re integrating powerful new AI features in Chrome that help you multitask across the web with a new side panel experience. We’re also bringing deeper integrations across our most popular Google Apps so you can be more productive, helping on complex multi-step workflows with auto browse and, in the coming months, you’ll get more contextually relevant help with Personal Intelligence. The new Gemini in Chrome is like having an assistant that helps you find information and get things done on the web easier than ever before.
Introducing a new way to browse with side panel: multitasking, reimagined
We're launching a new side panel experience so Gemini in Chrome users can always have a browsing assistant at your side, no matter what tab you're in. This can help you save time and multitask without interruption. You can keep your primary work open on one tab while using the side panel to handle a different task. Our testers have been using it for all sorts of things: comparing options across too-many-tabs, summarizing product reviews across different sites, and helping find time for events in even the most chaotic of calendars.
Gemini in Chrome now opens in a side panel, for easier multitasking.
Transform images on the web with Nano Banana
We’re also bringing the creative power of Nano Banana directly into Chrome, allowing you to transform images on the fly without needing to download and re-upload images or open another tab. Available to all Gemini in Chrome users, just type a prompt in the side panel to explain what you’re trying to do. Use it to get creative inspiration for a living room redesign or transform research data into stunning infographics.
No need for copy-pasting or re-uploading; Gemini in Chrome uses Nano Banana to transform images in your current browser window.
Get things done across Connected Apps
Gemini in Chrome supports Connected Apps, like integrations to Gmail, Calendar, YouTube, Maps, Google Shopping and Google Flights. These deeper integrations help you get things done, quickly. For example, if you’re traveling to a conference and need to book a flight, Gemini can dig up that old email with event details, reference context from Google Flights to provide some recommendations, and later draft an email letting your colleagues know your arrival time. These features can be enabled in the Connected Apps section of Gemini Settings.
Gemini in Chrome works with other Google apps, such as Gmail.
Personal Intelligence: A more personal, proactive Chrome
People have found it helpful to have Personal Intelligence in the Gemini app, and in the coming months we’ll bring it to Chrome. With Personal Intelligence, you’re always in control. You can opt-in and choose whether to connect your apps and disconnect them at any time.
Chrome will remember context from past conversations so you get uniquely tailored answers to whatever you're looking for across the web and you can already add specific instructions to Gemini to get more tailored responses. Personal Intelligence in Chrome transforms the browsing experience from a general purpose tool into a trusted partner that understands you and provides relevant, proactive and context-aware assistance.
Save time by letting Chrome auto browse handle the work for you
For years, Chrome autofill has handled the small stuff, like automatically entering your address or credit card, to help you finish tasks faster. Today, Chrome is advancing beyond simple tasks to helping with agentic action, allowing you to offload complex travel logistics or get help with professional workflows. For AI Pro and Ultra subscribers in the U.S., we're introducing Chrome auto browse 2 — a powerful agentic experience that handles multi-step chores on your behalf.
Auto browse can help you optimize your vacation planning by doing some of the mundane work, like researching hotel and flight costs across multiple date options, so you can find a budget-friendly time to travel. Our testers have used it for all sorts of things: scheduling appointments, filling out tedious online forms, collecting their tax documents, getting quotes for plumbers and electricians, checking if their bills are paid, filing expense reports, managing their subscriptions and speeding up renewing their driving licenses — a ton of time saved.
You can use it for more complicated things too: Let’s say you’re planning a Y2K theme party and find inspiration in a photo that perfectly captures that era. Auto browse, with the multimodal capabilities of Gemini 3, can identify what’s in the picture, search for similar items and add them to your cart — staying within budget and even applying discount codes. And if you give auto browse permission, it can use Google Password Manager to handle tasks even if a sign-in is required.
Understanding your creative vision, Gemini in Chrome can help you look up very specific party decorations and put them into the cart.
Gemini in Chrome with new agentic capabilities — auto browse — can fill in forms for you, for example, with information from a PDF.
Gemini in Chrome can recommend the best weekend for your stay based on your criteria for hotels and flights.
Gemini in Chrome can help you find the right apartment, filtering results for you based on your criteria.
Finally, Chrome will support Google’s Universal Commerce Protocol (UCP), a new open standard for agentic commerce co-developed with industry leaders including Shopify, Etsy, Wayfair and Target. This new open standard ensures that AI agents can take actions on a user's behalf seamlessly in Chrome.
Security and control by design
We’ve built Gemini in Chrome with rigorous security standards and introduced entirely new defenses to help protect you from new types of online threats. And for added control, auto browse is designed to pause and explicitly ask for your confirmation or prompt you to complete some tasks like making a purchase or posting on social media.
Auto browse capabilities are designed to keep you in the loop and ask for confirmation of sensitive actions.
We’re just beginning to explore the possibilities of an agentic web, and we can’t wait to see how these new features help you stay inspired and get more done in Chrome.