深度研究功能介绍

概述 Overview

2026 年 2 月 10 日更新： 现在你可以将深度研究连接到任何 MCP 或应用，并将网络搜索限制在可信站点，从而专注于经过认证的行业标准来源。你还可以实时跟踪进度，并通过后续提示或新来源进行中断以优化。我们更新了视觉体验，使从开始到跟踪再到审查研究的整个过程更加便捷。

February 10, 2026 update: _You can now connect deep research to any MCP or app and restrict web searches to trusted sites, so you can focus on authenticated, industry-standard sources. You can also now track progress in real-time and interrupt to refine with follow-up prompts or new sources. We've updated the visual experience so it's easier to start, track, and review your research from end to end._

2025 年 7 月 17 日更新： 深度研究现在可以借助 ChatGPT 智能体中的可视化浏览器，进行更深入、更广泛的研究。要使用这些更新后的功能，只需从作曲家的下拉菜单中选择“智能体模式”，然后直接输入你的查询。原始的深度研究功能仍可通过工具菜单中的“深度研究”选项使用。

July 17, 2025 update: _Deep research can now go even deeper and broader with access to a visual browser as part of ChatGPT agent. To access these updated capabilities, simply select “agent mode” from the dropdown in the composer and enter your query directly. The original deep research functionality remains available via the “deep research” option in the tools menu._

2025 年 4 月 24 日更新： _我们大幅提高了深度研究的使用频率——Plus、Team、Enterprise 和 Edu 用户现在每月可获得 25 次查询，Pro 用户 250 次，免费用户 5 次。这得益于由 o4-mini 版本驱动的全新轻量版深度研究，它在保持高质量的同时更具成本效益。一旦达到完整版的使用上限，你的查询将自动切换到轻量版。_

_April 24, 2025 update__: We’re significantly increasing how often you can use deep research—Plus, Team, Enterprise, and Edu users now get 25 queries per month, Pro users get 250, and Free users get 5. This is made possible through a new lightweight version of deep research powered by a version of o4-mini, designed to be more cost-efficient while preserving high quality. Once you reach your limit for the full version, your queries will automatically switch to the lightweight version._

2025 年 2 月 25 日更新： 所有 Plus 用户现在都可以使用深度研究。

_February 25, 2025 update__: All Plus users can now use deep research._

2025 年 2 月 5 日更新： 深度研究现已面向英国、瑞士和欧洲经济区的 Pro 用户开放。

_February 5, 2025 update__: Deep research is now available to Pro users in the United Kingdom, Switzerland, and the European Economic Area._

今天，我们在 ChatGPT 中推出深度研究，这是一种新的智能体式能力，能够针对复杂任务在互联网上执行多步研究。它能在几十分钟内完成人类需要数小时才能完成的工作。

Today we’re launching deep research in ChatGPT, a new agentic capability that conducts multi-step research on the internet for complex tasks. It accomplishes in tens of minutes what would take a human many hours.

深度研究是 OpenAI 的下一个智能体，可以独立为你工作——你给出提示，ChatGPT 就会查找、分析并综合数百个在线来源，生成一份研究分析师级别的综合报告。它由即将推出的 OpenAI o3 模型的一个版本驱动，该版本针对网络浏览和数据分析进行了优化，利用推理来搜索、解释和分析互联网上的大量文本、图像和 PDF，并根据遇到的信息灵活调整方向。

Deep research is OpenAI's next agent that can do work for you independently—you give it a prompt, and ChatGPT will find, analyze, and synthesize hundreds of online sources to create a comprehensive report at the level of a research analyst. Powered by a version of the upcoming OpenAI o3 model that’s optimized for web browsing and data analysis, it leverages reasoning to search, interpret, and analyze massive amounts of text, images, and PDFs on the internet, pivoting as needed in reaction to information it encounters.

综合知识的能力是创造新知识的先决条件。因此，深度研究标志着我们朝着开发 AGI 这一更广泛目标迈出了重要一步，我们一直将 AGI 视为能够产生新颖科学研究的能力。

The ability to synthesize knowledge is a prerequisite for creating new knowledge. For this reason, deep research marks a significant step toward our broader goal of developing AGI, which we have long envisioned as capable of producing novel scientific research.

为何构建深度研究 Why we built deep research

深度研究是为那些在金融、科学、政策、工程等领域从事高强度知识工作，且需要全面、精确、可靠研究的人打造的。它同样适用于那些在购买通常需要仔细研究的商品（如汽车、家电和家具）时，寻求超个性化推荐的挑剔购物者。每个输出都带有完整的文档记录，包括清晰的引用和思考总结，便于参考和验证信息。它在寻找需要浏览众多网站才能获得的、小众且非直观的信息方面尤为有效。深度研究通过让你仅需一次查询就能卸载并加速复杂的、耗时的网络研究，从而释放宝贵的时间。

Deep research is built for people who do intensive knowledge work in areas like finance, science, policy, and engineering and need thorough, precise, and reliable research. It can be equally useful for discerning shoppers looking for hyper-personalized recommendations on purchases that typically require careful research, like cars, appliances, and furniture. Every output is fully documented, with clear citations and a summary of its thinking, making it easy to reference and verify the information. It is particularly effective at finding niche, non-intuitive information that would require browsing numerous websites. Deep research frees up valuable time by allowing you to offload and expedite complex, time-intensive web research with just one query.

深度研究独立地发现、推理并整合来自网络各处的见解。为此，它通过使用与 OpenAI o1（我们的首个推理模型）相同的强化学习方法，在需要浏览器和 Python 工具使用的真实世界任务上进行了训练。虽然 o1 在编程、数学和其他技术领域展现了令人印象深刻的能力，但许多现实世界的挑战需要从多样化的在线来源中获取广泛的上下文和信息。深度研究在这些推理能力的基础上构建，以弥合这一差距，使其能够处理人们在工作和日常生活中面临的各种问题。

Deep research independently discovers, reasons about, and consolidates insights from across the web. To accomplish this, it was trained on real-world tasks requiring browser and Python tool use, using the same reinforcement learning methods behind OpenAI o1, our first reasoning model. While o1 demonstrates impressive capabilities in coding, math, and other technical domains, many real-world challenges demand extensive context and information gathering from diverse online sources. Deep research builds on these reasoning capabilities to bridge that gap, allowing it to take on the types of problems people face in work and everyday life.

如何使用深度研究 How to use deep research

在 ChatGPT 中，在消息撰写器中选择“深度研究”并输入你的查询。告诉 ChatGPT 你需要什么——无论是流媒体平台的竞争分析，还是关于最佳通勤自行车的个性化报告。你可以附加文件或电子表格来为你的问题添加上下文。一旦它开始运行，侧边栏会显示所采取步骤和所用来源的摘要。

In ChatGPT, select ‘deep research’ in the message composer and enter your query. Tell ChatGPT what you need—whether it’s a competitive analysis on streaming platforms or a personalized report on the best commuter bike. You can attach files or spreadsheets to add context to your question. Once it starts running, a sidebar appears with a summary of the steps taken and sources used.

深度研究可能需要 5 到 30 分钟来完成其工作，需要时间深入网络。在此期间，你可以离开或处理其他任务——研究完成后你会收到通知。最终输出以报告形式出现在聊天中——在接下来的几周内，我们还将添加嵌入式图像、数据可视化和其他分析输出到这些报告中，以提供额外的清晰度和背景。

Deep research may take anywhere from 5 to 30 minutes to complete its work, taking the time needed to dive deep into the web. In the meantime, you can step away or work on other tasks—you’ll get a notification once the research is complete. The final output arrives as a report within the chat – in the next few weeks, we will also be adding embedded images, data visualizations, and other analytic outputs in these reports for additional clarity and context.

与深度研究相比，GPT-4o 更适合实时、多模态对话。对于需要深度和细节的多方面、领域特定查询，深度研究能够进行广泛探索并引用每个主张，这是快速摘要与可作为工作产品的有充分文档、经过验证的答案之间的区别。

Compared to deep research, GPT‑4o is ideal for real-time, multimodal conversations. For multi-faceted, domain-specific inquiries where depth and detail are critical, deep research’s ability to conduct extensive exploration and cite each claim is the difference between a quick summary and a well-documented, verified answer that can be usable as a work product.

商业 大海捞针 医学研究 用户体验设计 购物 通用知识

Business Needle in a Haystack Medical Research UX Design Shopping General Knowledge

GPT-4o GPT-4o

帮我找出过去 10 年中，按 GDP 排名前 10 的发达国家和前 10 的发展中国家的 iOS 和 Android 采用率、想学习另一门语言的人口比例以及移动渗透率的变化。将这些信息以表格形式呈现，并将统计数据分列，同时针对 ChatGPT 当前活跃的市场，为新的 ChatGPT iOS 翻译应用提供目标市场建议。

Help me find iOS and android adoption rates, % who want to learn another language, and change in mobile penetration, over the past 10 years, for top 10 developed and top 10 developing countries by GDP. Lay this info out in a table and separate stats into columns, and include recommendations on markets to target for a new iOS translation app from ChatGPT, focusing on markets ChatGPT is currently active in.

由于数据限制，要全面收集过去十年中按 GDP 排名前 10 的发达和发展中国家的 iOS 和 Android 采用率、对学习另一门语言感兴趣的人口比例以及移动渗透率的变化数据具有挑战性。然而，基于现有信息，我们可以为基于 ChatGPT 的新 iOS 翻译应用提供目标市场的见解和建议。

Compiling comprehensive data on iOS and Android adoption rates, the percentage of populations interested in learning another language, and changes in mobile penetration over the past decade for the top 10 developed and developing countries by GDP is challenging due to data limitations. However, based on available information, we can provide insights and recommendations for targeting markets with a new iOS translation app powered by ChatGPT.

* iOS 和 Android 采用率：全球范围内，截至 2024 年，Android 占据约 70.93%的主导市场份额，而 iOS 约占 28.32%。在美国，iOS 以 58.81%的市场份额领先。其他发达国家如日本、加拿大、澳大利亚和英国也表现出对 iOS 设备的更高偏好。相比之下，印度和巴西等发展中国家 Android 设备更为普遍。

* iOS and Android Adoption Rates: Globally, Android holds a dominant market share of approximately 70.93%, while iOS accounts for about 28.32% as of 2024. In the United States, iOS leads with a 58.81% market share. Other developed countries like Japan, Canada, Australia, and the United Kingdom also show a higher preference for iOS devices. In contrast, developing countries such as India and Brazil have a higher prevalence of Android devices.

* 语言学习兴趣：虽然没有现成的对学习另一门语言感兴趣的人口比例具体数据，但 Duolingo 等语言学习应用的全球流行度表明兴趣显著，该应用在 2024 年 7 月约有 1430 万次下载。这种兴趣在语言多样性较高或英语非主要语言的国家可能更高。

* Interest in Language Learning: While specific percentages of populations interested in learning another language are not readily available, the global popularity of language learning apps like Duolingo, which had approximately 14.3 million downloads in July 2024, indicates a significant interest. This interest is likely higher in countries with diverse linguistic landscapes or where English is not the primary language.

* 过去十年的移动渗透率：全球手机拥有量大幅增长。在美国，智能手机拥有率从 2011 年的 35%增加到 2024 年的 91%。发展中国家的移动渗透率也经历了显著增长，促进了数字服务的普及。

* Mobile Penetration Over the Past Decade: Mobile phone ownership has seen substantial growth globally. In the United States, smartphone ownership increased from 35% in 2011 to 91% in 2024. Developing countries have also experienced significant growth in mobile penetration, contributing to increased access to digital services.

考虑到现有数据并聚焦于 ChatGPT 当前活跃的市场，以下发达国家是新的 iOS 翻译应用的有前景目标：

Considering the available data and focusing on markets where ChatGPT is currently active, the following developed countries are promising targets for a new iOS translation app:

* 美国：高 iOS 市场份额和对语言学习的显著兴趣。

* United States: High iOS market share and significant interest in language learning.

* 英国：庞大的 iOS 用户群和多元文化人口，具有多样化的语言需求。

* United Kingdom: Substantial iOS user base and a multicultural population with diverse language needs.

* 加拿大：显著的 iOS 采用率和双语人口（英语和法语），增加了对翻译服务的需求。

* Canada: Notable iOS adoption and a bilingual population (English and French), increasing the demand for translation services.

在发展中国家，以下国家值得关注：

Among developing countries, the following are noteworthy:

* 中国：尽管 Android 占主导，但庞大的人口和对英语及其他语言日益增长的兴趣带来了重大机遇。

* China: Despite Android's dominance, the large population and growing interest in English and other languages present a significant opportunity.

* 印度：Android 使用率高，但不断增长的中产阶级带来 iOS 采用率的提升，以及对语言学习（尤其是英语）的强烈兴趣。

* India: High Android usage, but a growing middle class with increasing iOS adoption and a strong interest in language learning, especially English.

* 巴西：主要是 Android 用户，但语言学习应用市场可观，尤其是英语和西班牙语。

* Brazil: Predominantly Android users, but with a sizable market for language learning apps, particularly for English and Spanish.

聚焦这些市场与 ChatGPT 当前的可用性相符，并能利用现有的移动采用趋势和语言学习兴趣。

Focusing on these markets aligns with ChatGPT's current availability and leverages existing mobile adoption trends and language learning interests.

深度研究 Deep research

帮我查找过去 10 年中，按 GDP 排名前 10 的发达国家和前 10 的发展中国家的 iOS 和 Android 采用率、想学习另一门语言的人口比例以及移动渗透率的变化。将这些信息以表格形式呈现，并将统计数据分列，同时针对 ChatGPT 目前活跃的市场，为 ChatGPT 的新 iOS 翻译应用提供目标市场建议。

Help me find iOS and android adoption rates, % who want to learn another language, and change in mobile penetration, over the past 10 years, for top 10 developed and top 10 developing countries by GDP. Lay this info out in a table and separate stats into columns, and include recommendations on markets to target for a new iOS translation app from ChatGPT, focusing on markets ChatGPT is currently active in.

前 10 大发达经济体（按 GDP）——智能手机操作系统份额、语言学习兴趣和移动渗透率增长

Top 10 Developed Economies (by GDP) – Smartphone OS Share, Language-Learning Interest, and Mobile Penetration Growth

国家 iOS 市场份额 Android 市场份额对新语言的兴趣

CountryiOS Market ShareAndroid Market ShareInterest in New Language

（占人口百分比）移动渗透率变化（2013→2023）

(% of population)Mobile Penetration Change (2013→2023)

（美国）~58% iOS vs 42% Android （见左）高：

(USA)~58% iOS vs 42% Android _(see left)_High:

70%的人后悔失去外语能力（表明有强烈的提高意愿）56%→82%

70% regret losing foreign-language ability (indicating strong desire to improve)56%→82%

日本~69% iOS vs 31% Android （见左）高：

Japan~69% iOS vs 31% Android _(see left)_High:

德国~39% iOS vs 60% Android （见左）高：

Germany~39% iOS vs 60% Android _(see left)_High:

86%的欧洲人认为每个人都应至少会说一门外语（强烈的亲语言态度）40%→82%

86% of Europeans say everyone should speak ≥1 foreign language (strong pro-language attitude)40%→82%

（英国）~52% iOS vs 47% Android （见左）中高：

(UK)~52% iOS vs 47% Android _(see left)_Moderate-High:

约 73%有一定兴趣（仅 27%对新语言“无兴趣”）62%→82%

~73% have some interest (only 27% “no interest” in new languages)62%→82%

法国~35% iOS vs 64% Android （见左）高：

France~35% iOS vs 64% Android _(see left)_High:

86%（欧盟平均值）支持多语言；英语被广泛视为重要语言 42%→83%

86% (EU average) favor multilingualism; English widely seen as important42%→83%

意大利~30% iOS vs 69% Android （见左）高：

Italy~30% iOS vs 69% Android _(see left)_High:

86%（欧盟平均值）支持语言学习；四分之一的人后悔没有学习另一门语言 41%→85%

86% (EU avg.) favor language learning; 1 in 4 regret not learning another41%→85%

加拿大~60% iOS vs 40% Android （见左）中等：

Canada~60% iOS vs 40% Android _(see left)_Moderate:

许多人会双语（英语/法语）；对第三语言的兴趣上升（近期无百分比数据）56%→约 80%

Many bilingual (English/French); rising interest in third languages (no recent % data)56%→~80%

韩国~24% iOS vs 76% Android （见左）中等：

South Korea~24% iOS vs 76% Android _(see left)_Moderate:

英语教育重点突出；约 40%的青少年正在学习英语 73%→约 95%

Strong English education focus; ~40% of teens are learning English73%→~95%

（↑约 22 个百分点）——2013 年已非常高（现在接近饱和）

(↑ ~22 pp) – already very high by 2013 (near saturation now)

澳大利亚~55% iOS vs 45% Android （见左）中等：

Australia~55% iOS vs 45% Android _(see left)_Moderate:

约 70%的人认为学习语言有价值（英语占主导，但对亚洲语言的兴趣在增长）65%→约 85%

~70% see learning languages as valuable (English dominant but interest in Asian languages growing)65%→~85%

西班牙~20% iOS vs 79% Android （见左）高：

Spain~20% iOS vs 79% Android _(see left)_High:

88%的西班牙人在学校学习过外语（如英语）；强烈的文化兴趣 55%→约 85%

88% of Spaniards learned a foreign language in school (e.g. English); strong cultural interest55%→~85%

（↑约 30 个百分点）（估计，接近西欧同行）

(↑ ~30 pp) (est., nearing Western Europe peers)

前 10 大发展中/新兴经济体（按 GDP）——（考虑 ChatGPT 可用性）

Top 10 Developing/Emerging Economies (by GDP) – (ChatGPT availability considered)

国家 iOS 市场份额 Android 市场份额对新语言的兴趣

CountryiOS Market ShareAndroid Market ShareInterest in New Language

（显著统计）移动渗透率变化（2013→2023）

(notable stats)Mobile Penetration Change (2013→2023)

_^（ChatGPT 受限）_约 24% iOS vs 75% Android （见左）非常高：

^(ChatGPT restricted)~24% iOS vs 75% Android _(see left)_Very High:

数亿人在学习英语（但 ChatGPT 无法正式访问）47%→68%

Hundreds of millions learning English (but ChatGPT not officially accessible)47%→68%

印度~4% iOS vs 95% Android （见左）高：

India~4% iOS vs 95% Android _(see left)_High:

许多学校强制学英语；强烈的经济动机（80%的人将英语与更高收入联系起来）约 5%→46%

English compulsory in many schools; strong economic motivation (80% link English to higher income)~5%→46%

（↑约 41 个百分点）（智能手机采用率大幅跃升）

(↑ ~41 pp) (huge jump in smartphone adoption)

巴西~18% iOS vs 82% Android （见左）高：

Brazil~18% iOS vs 82% Android _(see left)_High:

对英语的巨大需求——只有约 5%的人会说英语，但大多数人将其视为关键技能 26%→67%

Great demand for English – only ~5% speak it, but most see it as key skill26%→67%

_^（ChatGPT 受限）_约 30% iOS vs 69% Android （见左）中等：

^(ChatGPT limited)~30% iOS vs 69% Android _(see left)_Moderate:

英语学习很普遍（学校强制）；存在兴趣，但 ChatGPT 可用性不确定 36%→74%

English learning common (compulsory in school); interest exists but ChatGPT availability is uncertain36%→74%

墨西哥~24% iOS vs 76% Android （见左）高：

Mexico~24% iOS vs 76% Android _(see left)_High:

为美国工作/移民而学习英语的强烈愿望；约 50%的学生在学校学习英语（估计）37%→62%

Strong desire to learn English for US job/migration; ~50% of students study English in school (est.)37%→62%

印度尼西亚~12% iOS vs 88% Android （见左）高：

Indonesia~12% iOS vs 88% Android _(see left)_High:

英语被视为入门技能；政府提高英语水平的项目<30%→68%

English seen as gateway skill; government programs to improve English proficiency<30%→68%

土耳其~15% iOS vs 85% Android（估计）（见左）高：

Turkey~15% iOS vs 85% Android (est.)_(see left)_High:

英语受到高度重视（教育中普遍）；

English highly valued (universal in education);

沙特阿拉伯~24% iOS vs 76% Android （见左）中等：

Saudi Arabia~24% iOS vs 76% Android _(see left)_Moderate:

英语广泛教授；92%的智能手机拥有率（许多人已经会英语/阿拉伯语双语）73%→约 95%

English widely taught; 92% smartphone ownership (many already bilingual in English/Arabic)73%→~95%

（↑约 22 个百分点）（早期采用者；现在接近饱和）

(↑ ~22 pp) (early adopter; near saturation now)

南非~16% iOS vs 83% Android （见左）高：

South Africa~16% iOS vs 83% Android _(see left)_High:

多语言社会；英语和阿非利卡语与本土语言一起教授——学习其他语言的文化动力 40%→约 60%

Multilingual society; English and Afrikaans taught alongside native languages – cultural impetus to learn others40%→~60%

阿根廷~12% iOS vs 88% Android （见左）高：

Argentina~12% iOS vs 88% Android _(see left)_High:

对英语的强烈兴趣（阿根廷在拉丁美洲英语水平领先）31%→约 70%

Strong interest in English (Argentina leads Latin America in English proficiency)31%→~70%

（↑约 39 个百分点）（估计，随着智能手机采用率急剧上升）

(↑ ~39 pp) (est., sharp rise with smartphone adoption)

来源：智能手机操作系统份额来自 StatCounter/Statista 数据（2023-24）。语言兴趣指标来自 Preply、Eurobarometer、Babbel 等调查（例如英国 73%兴趣；美国 70%后悔缺乏语言能力；日本>50%想学英语；Pearson 全球调查）。移动渗透率以智能手机拥有率衡量——过去十年中，发展中市场增长显著（例如巴西+40 个百分点），发达市场饱和度高（例如英国约 82%）。

Sources: Smartphone OS shares are from StatCounter/Statista data (2023–24). Language-interest metrics come from surveys by Preply, Eurobarometer, Babbel, etc. (e.g. UK 73% interest; US 70% regret lack of languages; Japan >50% want English; Pearson global survey). Mobile penetration is measured as smartphone ownership percentage – dramatic growth is noted in developing markets (e.g. Brazil +40 points) and high saturation in developed ones (e.g. UK ~82%) over the last decade.

建议：基于以上数据，对于新的 ChatGPT 驱动的 iOS 翻译应用，主要目标应是拥有大量 iOS 用户群和强烈语言学习需求、且 ChatGPT 可访问的国家。值得注意的是，日本、美国、英国、加拿大和澳大利亚是首选。这些市场结合了高 iOS 采用率（50-60%以上）和对语言学习的显著热情——例如，日本的 iPhone 主导地位和广泛的学习英语愿望使其成为理想选择。英语国家如美国、英国、加拿大和澳大利亚，尽管是单语社会，但对学习其他语言（如西班牙语或法语）表现出浓厚兴趣，且所有国家的智能手机渗透率均超过 80%，拥有数百万 iPhone 用户。

Recommendations: Based on the above, prime targets for a new ChatGPT‑powered iOS translation app would be countries with large iOS user bases_and_strong language-learning demand, where ChatGPT is accessible. Notably, Japan, the U.S., UK, Canada, and Australia emerge as top choices. These markets pair high iOS adoption (50–60%+ share) with significant enthusiasm for language learning – for example, Japan’s iPhone dominance and widespread desire to learn English make it ideal. English-speaking countries like the US, UK, Canada, and Australia, despite being monolingual societies, show substantial interest in learning other languages (e.g. Spanish or French), and all have over 80% smartphone penetration and millions of iPhone users.

在新兴经济体中，墨西哥和巴西是次要目标：尽管 Android 占主导，但其庞大的人口规模意味着存在数千万 iPhone 用户，并且出于职业和教育原因，对英语的兴趣非常高。这些拉丁美洲市场（ChatGPT 活跃）可能为仅限 iOS 的应用带来强劲的采用率，尤其是考虑到学习英语的动机。相反，中国和俄罗斯可行性较低——中国的操作系统份额偏向 Android，且 ChatGPT 未正式可用；俄罗斯面临访问和监管不确定性。

Among emerging economies, Mexico and Brazil stand out as secondary targets: although Android prevails, their sheer population sizes mean tens of millions of iPhone users exist, and interest in English is very high for career and education reasons. These Latin American markets (where ChatGPT is active) could yield strong adoption for an iOS-only app, especially given the motivation to learn English. Conversely, China and Russia are less feasible – China’s OS split skews Android and ChatGPT is not officially available there, and Russia faces access and regulatory uncertainties.

总之，应聚焦于 iOS 占比高、支持学习的市场：日本和西方国家（美国、英国、加拿大、澳大利亚，以及高收入的欧洲国家如德国和法国，程度稍低）应作为第一梯队目标。它们结合了强劲的 iOS 使用率和有利的语言学习态度。第二梯队包括人口众多的发展中市场（墨西哥、巴西，或许还有历史上 iPhone 采用率高的沙特阿拉伯），这些市场对英语的兴趣强烈——一旦应用在第一梯队市场获得 traction，就可以进入这些市场。这样的策略确保应用在平台（iOS）存在和用户对翻译/语言工具需求最匹配的地方推出，从而最大化采用和增长的可能性。

In summary, focus on iOS-heavy, pro-learning markets: Japan and Western countries (US, UK, Canada, Australia, plus high-income Europe like Germany and France to a lesser degree) should be the first-tier targets. They combine robust iOS usage with favorable language-learning attitudes. A second tier includes large-population developing markets (Mexico, Brazil, perhaps Saudi Arabia for its historically high iPhone uptake) where interest in English is strong – these can be approached once the app gains traction in the primary markets. Such a strategy ensures the app launches where it has the greatest alignment of platform (iOS) presence and user demand for translation/language tools, maximizing the likelihood of adoption and growth.

深度研究以高度详细的方式回应提示，为前 10 个发达国家和前 10 个发展中国家提供了并排的国家特定数据，便于参考和比较。它利用这些信息提供了基于数据且可操作的市场进入建议。

Deep research responds to the prompt in a highly detailed manner, providing side-by-side country-specific data for both top 10 developed and top 10 developing countries for easy reference and comparison. It uses that information to offer detailed market-entry recommendations that are informed and usable.

工作原理 How it works

深度研究通过端到端强化学习在多个领域的困难浏览和推理任务上进行训练。通过这种训练，它学会了规划和执行多步轨迹以寻找所需数据，在必要时回溯并实时响应信息。该模型还能够浏览用户上传的文件，使用 Python 工具绘制和迭代图表，在回复中嵌入生成的图表和网站图片，并引用来源中的特定句子或段落。经过这种训练，它在多个聚焦于现实世界问题的公开评估中达到了新的高度。

Deep research was trained using end-to-end reinforcement learning on hard browsing and reasoning tasks across a range of domains. Through that training, it learned to plan and execute a multi-step trajectory to find the data it needs, backtracking and reacting to real-time information where necessary. The model is also able to browse over user uploaded files, plot and iterate on graphs using the python tool, embed both generated graphs and images from websites in its responses, and cite specific sentences or passages from its sources. As a result of this training, it reaches new highs on a number of public evaluations focused on real-world problems.

人类的最后考试 Humanity's Last Exam

在最近发布的“人类的最后考试”中，该评估在广泛学科领域以专家级问题测试 AI，驱动深度研究的模型以 26.6%的准确率创下新高。该测试包含超过 3000 道选择题和简答题，涵盖从语言学、火箭科学到古典学、生态学等 100 多个学科。与 OpenAI o1 相比，最大的进步出现在化学、人文与社会科学以及数学领域。驱动深度研究的模型展现出类似人类的方法，在必要时有效寻找专业信息。

On Humanity’s Last Exam⁠(opens in a new window), a recently released evaluation that tests AI across a broad range of subjects on expert-level questions, the model powering deep research scores a new high at 26.6% accuracy. This test consists of over 3,000 multiple choice and short answer questions across more than 100 subjects from linguistics to rocket science, classics to ecology. Compared to OpenAI o1, the largest gains appeared in chemistry, humanities and social sciences, and mathematics. The model powering deep research showcased a human-like approach by effectively seeking out specialized information when necessary.

* 模型非多模态，仅在纯文本子集上评估。

* Model is not multi-modal, evaluated on text-only subset.

GAIA GAIA

在 GAIA¹（一个评估 AI 处理现实世界问题的公开基准测试）上，驱动深度研究的模型达到了新的最先进水平（SOTA），登顶外部排行榜¹。该基准测试包含三个难度级别的问题，成功完成这些任务需要具备推理、多模态流畅性、网页浏览和工具使用熟练度等能力。

On GAIA⁠(opens in a new window)1, a public benchmark that evaluates AI on real-world questions, the model powering deep research reaches a new state of the art (SOTA), topping the external leaderboard⁠(opens in a new window). Encompassing questions across three levels of difficulty, successful completion of these tasks requires abilities including reasoning, multi-modal fluency, web browsing, and tool-use proficiency.

GAIA 任务示例 GAIA task examples

在 2012 年《自然》期刊的《科学报告》会议论文集中，有一篇未提及等离激元或等离激元学的文章，其中研究了哪种纳米化合物？如果答案中有前缀 nano，请勿使用。

In Nature journal's Scientific Reports conference proceedings from 2012, in the article that did not mention plasmons or plasmonics, what nano-compound is studied? Don't use the prefix nano in your answer if there is one.

[剩余的思维链消息和最终答案被隐藏，以保护基准测试的真实答案。]

[The remaining Chain-of-Thought messages and the final answer are hidden to protect the benchmark's ground truth answer.]

我正在梳理一个请求，要求从 2012 年的《科学报告》中找出一篇描述纳米化合物的文章，排除任何与等离激元学相关的文章。这可能涉及过滤特定主题或化合物，如银或石墨烯。

I’m piecing together the request for an article from 2012 in Scientific Reports that details a nano-compound, excluding any related to plasmonics. Likely, this involves filtering specific topics or compounds, like silver or graphene.

我正在子搜索“Scientific Reports 2012 nanoparticle”，可能寻找纳米化合物。有兴趣过滤掉与等离激元相关的主题，可能关注银、石墨烯或量子点。

I'm sub-searching "Scientific Reports 2012 nanoparticle," likely seeking nano-compounds. Interested in filtering out plasmon-related topics, possibly focusing on silver, graphene, or quantum dots.

我正在深入挖掘 nature.com 和《科学报告》上 2012 年的高级搜索过滤器，试图精确定位关于食品焦糖中无定形碳纳米颗粒的文章。

I’m digging into advanced search filters on nature.com and Scientific Reports for 2012, trying to pinpoint articles on amorphous carbon nanoparticles in food caramels.

搜索结果揭示了一篇 2012 年的会议论文，题为“2D quasiperiodic plasmonic crystals”，可能出现在《科学报告》的“会议论文集”类别下。

The search results reveal a conference proceeding titled "2D quasiperiodic plasmonic crystals" from 2012, likely found under the "Conference Proceedings" category in Scientific Reports.

我正在考虑网页误解的原因，可能是由于过时的智能体类型或无意中的阻塞。

I'm considering the reasons behind a web page misconception, likely due to an outdated agent type or inadvertent blockage.

我在考虑一个具有动态内容或缓存版本的自然网站。或者，尝试搜索特定短语可能会有所帮助。

I'm thinking about a nature site with dynamic content or a cached version. Alternatively, trying a search for specific phrases might help.

好的，我正在识别 2012 年《科学报告》中的四篇会议论文。值得注意的是，有些提到了“plasmonic”，应予以排除。

OK, I'm identifying four conference proceedings from 2012 in Sci Rep. Notably, some mention "plasmonic" and should be excluded.

我正在收集关于访问特定标题的缓存版本或片段扩展的信息，以确保全面分析。

I’m gathering info on accessing cached versions or snippet expansions for specific titles to ensure comprehensive analysis.

我注意到从 2012 年欧洲材料研究学会春季会议到科学报告的进展，重点关注会议论文集。这种方法有助于建立背景和相关性。

I’m noting the progression from the 2012 European Materials Research Society Spring Meeting to the scientific report, focusing on conference proceedings. This approach helps establish context and relevance.

尝试将 2012 年末的会议论文集与《科学报告》期刊联系起来，重点关注等离激元二维准周期材料。这种方法感觉有条理且精确。

Trying to connect conference proceedings from late 2012 with "Scientific Reports" journal, focusing on plasmonic 2D quasiperiodic materials. This approach feels methodical and precise.

注意到搜索结果 [8] 包含一个可能总结欧洲材料研究学会 2012 年春季会议的页面，包括 25 个专题讨论会。

Noting that the search results [8] include a page likely summarizing the European Materials Research Society 2012 Spring Meeting, including 25 symposia.

我正在检查一个可能包含 4 篇文章的集合页面，考虑等离激元和超材料主题，并识别来自欧洲材料研究学会 2012 年春季会议的关键参考文献。

I’m examining a likely collection page with 4 articles, considering plasmonic and metamaterial topics, and identifying key references from the European Materials Research Society 2012 Spring Meeting.

我专注于 2012 年《科学报告》中来自 E-MRS 的会议论文集，可能涉及“2D quasiperiodic plasmonic crystals”和“Layered plasmonic cloaks to tailor the optical scattering at the nanoscale”等主题。

I’m focusing on the 2012 conference proceedings in "Scientific Reports" from E-MRS, likely involving topics like "2D quasiperiodic plasmonic crystals" and "Layered plasmonic cloaks to tailor the optical scattering at the nanoscale."

考虑 E-MRS 2012 年《科学报告》特邀论文特刊 Monticone 和超材料实验室，新闻档案 – 2012。

Thinking about special issue E-MRS 2012 Sci rep invited paper Monticone and metamaterials lab at News Archives – 2012.

我正在收集关于潜在网站访问问题的信息，考虑过时状态或阻塞。同时，评估 Monticone 网站以获取列表参考。

I'm gathering info on potential site access issues, considering outdated status or blockages. Also, evaluating the Monticone site for a list reference.

我试图将“Layered Plasmonic Cloaks”与 E-MRS 2012 联系起来。考虑其他可能的主题，如石墨烯和催化。

I'm trying to link "Layered Plasmonic Cloaks" to E-MRS 2012. Considering other possible topics like graphene and catalysis.

我正在收集关于石墨烯、光伏和纳米结构化合物等主题的信息，同时排除与等离激元相关的主题。这使我更广泛地关注纳米技术方面。

I’m gathering info on topics like graphene, photovoltaics, and nanostructured compounds, while excluding plasmonic-related ones. This leads me to focus on nanotechnology aspects more broadly.

我通过输入特定的网站和学者标识符来扩大搜索参数，以精确定位《自然·科学报告》2012 年中关于二维准周期等离激元晶体的文章。

I’m broadening the search parameters by entering specific site and scholar identifiers to pinpoint articles about 2D quasiperiodic plasmonic crystals in Nature Scientific Reports from 2012.

我正在缩小搜索范围，以识别《科学报告》2012 年 E-MRS 特刊中的文章。这涉及检查标题中非等离激元的主题，如石墨烯或功能氧化物。通过聚焦搜索和排除等离激元文章，进展明显。

I'm narrowing down the search to identify articles from the 2012 E-MRS special issue in Scientific Reports. This involves checking titles for non-plasmonic topics, like graphene or functional oxides. Progress is evident through focused searches and exclusion of plasmonic articles.

我正在分析石墨烯超晶格中的相互作用，可能来自一篇《科学报告》文章。考虑作者如 Padooru、Yakovlev、Chen 和 Alu 的标题。

I'm analyzing interactions in a graphene superlattice, likely from a Sci Rep article. Considering titles by authors like Padooru, Yakovlev, Chen, and Alu.

我正在收集关于 E-MRS 2012 年春季会议《科学报告》论文集的信息，重点关注特邀论文，不包括等离激元现象。正在审查的类型包括石墨烯、催化、能源材料、纳米医学和传感器。

I’m gathering info on E-MRS 2012 Spring Meeting's Sci Rep proceedings, focusing on invited papers, without plasmonic phenomena. Types under review are graphene, catalysis, energy materials, nanomedicine, and sensors.

专家级任务 Expert-Level Tasks

在一项涵盖多个领域的专家级任务内部评估中，深度研究被领域专家评定为已自动化了数小时的困难人工调研。

In an internal evaluation of expert-level tasks across a range of areas, deep research was rated by domain experts to have automated multiple hours of difficult, manual investigation.

模型浏览得越多，并思考其浏览的内容，其表现就越好，这就是为什么给予它思考时间很重要。

The more the model browses and thinks about what its browsing, the better it does, which is why giving it time to think is important.

我是一位研究人员，有兴趣将混合气体吸附能力引入我的实验室。请讨论玻璃态聚合物中纯气体和混合气体吸附的差异，双模式吸附模型如何用于预测玻璃态聚合物中的混合气体吸附行为（包括适用的方程），以及使用双模式吸附模型准确预测纯气体和混合气体吸附存在哪些挑战。仅包含截至 2024 年 10 月 1 日的开源信息。

I am a researcher interested in bringing mixed-gas sorption capabilities to my lab. Please discuss the differences between pure- and mixed-gas sorption for glassy polymers, how the dual-mode sorption model can be used to predict mixed-gas sorption behavior in glassy polymers (include equations where applicable), and what challenges there are in accurately predicting pure- and mixed-gas sorption using the dual-mode sorption model. Only include open-source information as of October 1, 2024.

玻璃态聚合物中的纯气体与混合气体吸附：在玻璃态聚合物（低于$T_{g}$）中，单一气体通常呈现凹形吸附等温线：吸收量随压力呈亚线性增加，这与高于$T_{g}$时的线性亨利定律行为不同。这归因于“双模式”吸附：部分渗透剂溶解在致密的聚合物基体中（服从亨利定律），而额外的渗透剂则饱和特定的微空“位点”（聚合物非平衡自由体积中的朗缪尔型吸附）。相比之下，当存在两种或多种气体时，它们会竞争那些有限的朗缪尔吸附位点。因此，混合物中每种组分的吸附浓度通常低于相同分压下单独存在时的浓度。特别是，溶解度较低（亲和力较低）的气体往往受到更强的抑制，通常导致混合气体_溶解度选择性_（浓度比）超过纯气体等温线预测的理想值。例如，在 CO₂/CH₄混合物中，两种组分的吸附量都低于其纯气体情况（尤其是 CH₄），因此混合条件下的 CO₂/CH₄吸附选择性更高。在极端情况下，混合气体效应甚至可能逆转单气体观察到的性能趋势。（我们注意到，与竞争吸附不同，_协同_吸附——即一种气体通过聚合物溶胀增加另一种气体的吸附——在中等压力下的刚性高自由体积聚合物中通常较小。）

Pure vs. mixed-gas sorption in glassy polymers: In a glassy polymer (below $T_{g}$T g​), a single gas typically exhibits a concave sorption isotherm: uptake rises sublinearly with pressure, unlike the linear Henry’s-law behavior above $T_{g}$T g​. This is attributed to “dual-mode” sorption: some penetrant dissolves in the dense polymer matrix (obeying Henry’s law) while additional penetrant saturates specific microvoid “sites” (a Langmuir-type adsorption in the polymer’s nonequilibrium free volume). By contrast, when two or more gases are present, they compete for those limited Langmuir sorption sites. As a result, each component’s sorbed concentration in a mixture is generally lower than it would be at the same partial pressure alone. In particular the less soluble (lower-affinity) gas tends to be more strongly suppressed, often causing the mixed-gas solubility selectivity (ratio of concentrations) to exceed the ideal value predicted from pure-gas isotherms. For example, in CO₂/CH₄ mixtures both components sorb less than in their pure-gas cases (especially CH₄), so the CO₂/CH₄ sorption selectivity is higher under mixture conditions. In extreme cases, mixed-gas effects can even reverse performance trends observed with single gases. (We note that unlike competitive sorption, synergistic sorption – where one gas increases the sorption of another via polymer swelling – is usually minor in rigid high-free-volume polymers under moderate pressures.)

双模式吸附模型与混合气体预测：双模式吸附（DMS）模型通过叠加亨利定律项和朗缪尔项定量捕捉玻璃态聚合物的吸附。对于单一气体，吸附浓度$C$（例如，cm³(STP)气体/cm³聚合物）写为：

Dual-mode sorption model and mixed-gas prediction: The dual-mode sorption (DMS) model quantitatively captures glassy polymer sorption by superposing a Henry’s-law term and a Langmuir term. For a single gas, the sorbed concentration $C$C (e.g. in cm³(STP) gas per cm³ polymer) is written as:

$C \left(\right. p \left.\right) = k_{D} \textrm{ } p \textrm{ }\textrm{ } + \textrm{ }\textrm{ } \frac{C_{H}^{'} \textrm{ } b \textrm{ } p}{\textrm{ } 1 + b \textrm{ } p \textrm{ }} \textrm{ } .$

$C \left(\right. p \left.\right) = k_{D} \textrm{ } p \textrm{ }\textrm{ } + \textrm{ }\textrm{ } \frac{C_{H}^{'} \textrm{ } b \textrm{ } p}{\textrm{ } 1 + b \textrm{ } p \textrm{ }} \textrm{ } .$C(p)=k D​p+1+b p C H′​b p​.

这里$k_{D}$是溶解的亨利定律系数，$C_{H}^{'}$是朗缪尔容量常数（与聚合物的未松弛自由体积或“空穴”容量成正比），$b$是朗缪尔亲和常数。这个经验公式产生了玻璃态聚合物的特征凹形等温线，并在玻璃化转变时简化为简单的亨利定律（因为当$T \rightarrow T_{g}$时$C_{H}^{'} \rightarrow 0$）。通过拟合纯气体吸附数据获得相同的三个参数（$k_{D} , C_{H}^{'} , b$），然后用于预测混合物吸附。对于气体 A 和 B 的二元混合物（分压为$p_{A} , p_{B}$），DMS 模型假设每种气体服从其自身的亨利项，并且两者竞争相同的朗缪尔位点。一种方便的形式是将总吸附浓度写为每种气体贡献之和：

Here $k_{D}$k D​ is the Henry’s law coefficient for dissolution, $C_{H}^{'}$C H′​ is the Langmuir capacity constant (proportional to the polymer’s unrelaxed free-volume or “hole” capacity), and $b$b is the Langmuir affinity constant. This empirical formula yields the characteristic concave isotherm of glassy polymers and reduces to simple Henry’s law at the glass-transition (since $C_{H}^{'} \rightarrow 0$C H′​→0 as $T \rightarrow T_{g}$T→T g​). The same three parameters ($k_{D} , C_{H}^{'} , b$k D​,C H′​,b) are obtained by fitting pure-gas sorption data and are then used to predict mixture sorption. For a binary mixture of gases A and B (with partial pressures $p_{A} , p_{B}$p A​,p B​), the DMS model assumes each gas obeys its own Henry’s term and that both compete for the same Langmuir sites. One convenient form is to write the total sorbed concentration as the sum of contributions from each gas:

$C_{\text{tot}} = k_{D , A} p_{A} + k_{D , B} p_{B} \textrm{ }\textrm{ } + \textrm{ }\textrm{ } \frac{\textrm{ } C_{H , A}^{'} \textrm{ } b_{A} \textrm{ } p_{A} \textrm{ }\textrm{ } + \textrm{ }\textrm{ } C_{H , B}^{'} \textrm{ } b_{B} \textrm{ } p_{B} \textrm{ }}{\textrm{ } 1 + b_{A} p_{A} + b_{B} p_{B} \textrm{ }} \textrm{ } ,$

$C_{\text{tot}} = k_{D , A} p_{A} + k_{D , B} p_{B} \textrm{ }\textrm{ } + \textrm{ }\textrm{ } \frac{\textrm{ } C_{H , A}^{'} \textrm{ } b_{A} \textrm{ } p_{A} \textrm{ }\textrm{ } + \textrm{ }\textrm{ } C_{H , B}^{'} \textrm{ } b_{B} \textrm{ } p_{B} \textrm{ }}{\textrm{ } 1 + b_{A} p_{A} + b_{B} p_{B} \textrm{ }} \textrm{ } ,$C tot​=k D,A​p A​+k D,B​p B​+1+b A​p A​+b B​p B​C H,A′​b A​p A​+C H,B′​b B​p B​​,

这隐含着混合物中组分_i_的浓度为$C_{i} = k_{D , i} p_{i} + \frac{C_{H , i}^{'} b_{i} p_{i}}{\textrm{ } 1 + \sum_{j} b_{j} p_{j} \textrm{ }}$。当另一种组分的压力为零时，这简化为单气体公式。在实践中，这些方程中的分压通常被逸度取代以提高高压下的准确性，尽管如果一致应用，使用逸度或压力会得到几乎相同的结果。DMS 混合气体模型预测了实验观察到的竞争吸附效应——即每种气体的吸收量相对于其纯气体吸附等温线有所降低。

which implicitly means the concentration of component i in the mixture is $C_{i} = k_{D , i} p_{i} + \frac{C_{H , i}^{'} b_{i} p_{i}}{\textrm{ } 1 + \sum_{j} b_{j} p_{j} \textrm{ }}$C i​=k D,i​p i​+1+∑j​b j​p j​C H,i′​b i​p i​​. This reduces to the single-gas formula when the other component’s pressure is zero. In practice, partial pressure in these equations is often replaced by fugacity for accuracy at high pressures, though using fugacities or pressures gives nearly the same results if applied consistently. The DMS mixed-gas model predicts the competitive sorption effect observed experimentally – namely, each gas’s uptake is depressed relative to its pure-gas sorption isotherm.

挑战与局限性：尽管双模式模型在关联吸附数据方面取得了广泛成功，但在预测吸附行为方面存在显著局限性。首先，DMS 模型是经验性的——其拟合参数_并非_通用常数，而是随聚合物形成历史、物理老化和温度/压力范围而变化。这意味着在一组条件下获得的参数集可能在其校准范围之外缺乏预测能力。例如，仅在有限压力范围内测量的吸附等温线可以通过 DMS 很好地拟合，但外推超出该范围（特别是接近塑化压力）可能不可靠。事实上，$k_{D}$、$C_{H}^{'}$、$b$的多种不同组合有时可以几乎同样好地拟合相同的纯气体等温线——然而它们却产生截然不同的混合气体预测。这种敏感性削弱了对混合物预测的信心，因为一项研究表明，使用不同的纯气体拟合集仅与某些混合 CO₂/CH₄数据达到_定性_一致。

Challenges and limitations: Although the dual-mode model is widely successful in correlating sorption data, it has notable limitations in predicting sorption behavior. First, the DMS model is empirical – its fitted parameters are not universal constants but can vary with polymer formation history, physical aging, and temperature/pressure range. This means a parameter set obtained under one set of conditions may lack predictive power outside its calibration range. For instance, sorption isotherms measured only over a limited pressure range can be fit well by DMS, but extrapolating beyond that (especially approaching plasticization pressures) may be unreliable. Indeed, multiple distinct combinations of $k_{D}$k D​, $C_{H}^{'}$C H′​, $b$b can sometimes fit the same pure-gas isotherm almost equally well – yet they yield markedly different mixed-gas predictions. This sensitivity undermines confidence in mixture forecasts, as one study showed that using different pure-gas fit sets led to only qualitative agreement with some mixed-CO₂/CH₄ data.

此外，DMS 本质上假设朗缪尔位点（微空）的固定数量，并忽略吸附质引起的聚合物松弛或溶胀。实际上，渗透剂诱导的溶胀（塑化）可以增加自由体积和吸附容量，特别是对于高活性的高度可冷凝气体——这是基本 DMS 模型无法捕捉的效应。在二元吸附中，这意味着标准模型未考虑由于第二种气体（或由于聚合物膨胀）引起的任何协同吸附增加。相反，该模型也无法描述偏离凹形朗缪尔型行为的吸附等温线形状（例如，由特定聚合物-渗透剂相互作用或聚集引起的 S 形等温线）。例如，吸收极性分子（如醇类）的玻璃态聚合物可以显示 S 形吸附等温线，简单的双模式框架无法表示。最后，准确测量混合气体吸附本身具有挑战性，理想化模型假设（例如，真正为零的下游压力，无竞争扩散限制）与实验现实之间的差异可能增加预测误差。尽管存在这些挑战，双模式吸附模型——在适当谨慎的情况下——仍然是解释玻璃态聚合物吸附的有价值的一级近似，并强调了竞争性位点占据在混合气体环境中的关键作用。当双模式模型的假设失效时，研究人员通常会转向更精细的模型（例如，非平衡晶格流体或热力学理论），但这些模型以额外的参数或复杂性为代价。总之，双模式吸附为玻璃态聚合物中的纯气体和混合气体吸附提供了有用的基线，但在实践中预测多组分吸附行为时，必须注意其经验性质以及上述局限性。

Furthermore, DMS inherently assumes a fixed population of Langmuir sites (microvoids) and ignores polymer relaxation or swelling induced by sorbate. In reality, penetrant-induced swelling (plasticization) can increase free volume and sorption capacity, especially for highly condensable gases at high activity – an effect the basic DMS model cannot capture. In binary sorption, this means any synergistic increase in sorption due to a second gas (or due to polymer dilation) is unaccounted for in the standard model. Conversely, the model also cannot describe sorption isotherm shapes that deviate from concave Langmuir-type behavior (e.g. sigmoidal isotherms caused by specific polymer-penetrant interactions or clustering). For example, glassy polymers absorbing polar molecules like alcohols can show sigmoidal sorption isotherms, which the simple dual-mode framework fails to represent. Finally, accurately measuring mixed-gas sorption itself is challenging, and discrepancies between idealized model assumptions (e.g. truly zero downstream pressure, no competitive diffusion limitations) and experimental realities can add to prediction error. Despite these challenges, the dual-mode sorption model – with appropriate care – remains a valuable first approximation for interpreting sorption in glassy polymers, and it highlights the key role of competitive site occupancy in mixed-gas environments. Researchers often turn to more elaborate models (e.g. non-equilibrium lattice fluid or thermodynamic theories) when the dual-mode model’s assumptions break down, but such models come at the cost of additional parameters or complexity. In summary, dual-mode sorption provides a useful baseline for pure- and mixed-gas sorption in glassy polymers, but one must be mindful of its empirical nature and the above limitations when predicting multicomponent sorption behavior in practice.

来源：双模式吸附模型及混合气体扩展；混合物中的竞争吸附效应；模型方程与参数；DMS 模型的局限性；参数敏感性与预测性问题。

Sources: Dual-mode sorption model and mixed-gas extension; competitive sorption effects in mixtures; model equations and parameters; limitations of DMS model; parameter sensitivity and predictivity issues.

我正在收集关于玻璃态聚合物中纯气体和混合气体吸附的信息，重点关注双模式吸附模型并解决建模预测中的挑战。

I’m gathering info on pure and mixed-gas sorption in glassy polymers, focusing on the dual-mode sorption model and addressing challenges in modeling predictions.

好的，让我看看。来自 MDPI 关于玻璃态聚合物中混合气体吸附的结果可能是开放获取的。

OK, let me see. The result from MDPI on mixed-gas sorption in glassy polymers is probably open access.

我正在从双模式吸附模型及其在 MDPI 论文中的扩展分析中整合见解。

I’m pulling together insights from the Dual Mode Sorption Model and its extended analysis within the MDPI paper.

我正在检查实验报告，以了解亨利定律常数、朗缪尔亲和常数和朗缪尔容量常数，这些常数描述了气体吸附。

I’m examining the lab report to understand Henry's law constant, Langmuir affinity constant, and Langmuir capacity constant, which describe gas sorption.

我正在思考“方程(3)”和“方程(4)”可能是图像或公式显示的可能性，并考虑查阅 PDF 或搜索早期参考文献以更好地理解它们。

I'm working through the possibility that "Equation (3)" and "Equation (4)" might be images or formula displays and considering consulting the PDF or searching for earlier references to understand them better.

我正在验证来自 Freeman 和 Koros（1980）的文献是否与参考文献“玻璃态聚合物中混合气体吸附模型”完全匹配，通过检查其摘要和标题。

I’m verifying if the document from Freeman and Koros (1980) specifically matches the reference "Model for sorption of mixed gases in glassy polymers" by checking its abstract and title.

我注意到来自“pmc.ncbi.nlm.nih.gov”的结果很可能是同一篇 MDPI 文章，我很好奇它是否呈现了文本或简化版本。

I noticed that the result from "pmc.ncbi.nlm.nih.gov" is likely the same MDPI article, and I'm curious to see if it presents the text or a simplified version.

我正在收集关于玻璃态聚合物中纯气体和混合气体吸附的信息。这是理解材料在不同气体环境下行为的关键步骤。

I'm gathering information about pure and mixed gas sorption in glassy polymers. This is a critical step in understanding the material's behavior under different gas environments.

我注意到二氧化碳在混合物中的存在会影响聚合物中的甲烷吸附，与纯气体情况相比降低了甲烷的吸附。

I noticed that carbon dioxide's presence in a mixture affects methane sorption in polymer, reducing methane's sorption compared to a pure gas scenario.

我正在思考术语“扩展双模式方程混合物”可能与双模式超导电缆方程有关。这显示了跨领域连接概念的潜力。

I’m thinking through how the term "extended dual mode equation mixture" might relate to dual mode superconducting cable equations. This shows potential for connecting concepts across fields.

我注意到需要回顾“聚合物膜中的吸附与传输理论”。

I'm noting the request to review "Theories of Sorption and Transport in Polymer Membrane."

我对结果[2]感到好奇，并正在探索片段，其中涉及将双模式吸附模型扩展到二元混合物，并用分压和常数表示 A 的浓度。

I’m curious about Result [2] and exploring the snippet, which involves extending a dual-mode sorption model to a binary mixture and expressing concentration of A in terms of partial pressures and constants.

双模式模型预期添加第二种气体会在恒定分压下降低吸附，这与纯气体情况不同。

The dual-mode model anticipates that adding a second gas reduces sorption at a constant partial pressure, unlike pure gas scenarios.

我正在收集关于 nature.com PDF 的信息，可能是一篇较旧的 Yampol'ski 文章，但考虑替代来源，如德克萨斯大学奥斯汀分校的存储库，以获取文本片段。

I'm gathering info on a nature.com PDF, possibly an older Yampol'ski article, but thinking about alternative sources like the University of Texas at Austin repository for a text snippet.

我发现 UT 存储库的结果可能无法正确显示。在其中搜索是不确定的。或者，结果[3]包含一个描述双模式混合物吸附模型的片段，解释了竞争效应及其在建模实验数据中的充分性。

I’ve discovered that the UT repository result might not display correctly. Searching within it is uncertain. Alternatively, result [3] contains a snippet describing the dual mode mixture sorption model, explaining competitive effects and its adequacy in modeling experimental data.

我正在调整方法以确保搜索针对正确的上下文。

I'm adjusting my approach to ensure the search targets the right context.

我正在详细说明纯气体的双模式吸附模型：亨利溶解和朗缪尔微空填充。对于混合气体，强调了竞争吸附和非理想性。

I’m detailing the dual-mode sorption model for pure gases: Henry dissolving and Langmuir microvoid filling. For mixed gases, competitive sorption and non-idealities are emphasized.

思考 hero.epa.gov 可能的摘要或内容。

Thinking through hero.epa.gov's potential abstract or content.

我正在收集关于纯气体和混合气体吸附的见解，考虑竞争、塑化和参数稳定性等因素。纳入混合气体数据以获得更准确的预测。

I'm gathering insights on pure and mixed gas sorption, considering factors like competition, plasticization, and parameter stability. Incorporating mixed-gas data for more accurate predictions.

解决双吸附模型挑战

Addressing dual sorption model challenges

参数耦合和非唯一性影响预测。忽略聚合物条件变化可能导致疏忽。

Parameter coupling and non-uniqueness impact predictions. Absence of polymer condition changes might lead to oversights.

我正在量化 6FDA-mPDA 中的非理想 CO2-CH4 溶解度，显示混合气体对溶解度的影响。竞争吸附并非渗透选择性下降的唯一原因。

I’m quantifying nonideal CO2-CH4 solubility in 6FDA-mPDA, showing mixed gas effects on solubility. Competitive sorption isn’t the sole cause of permeability selectivity decline.

我正在收集引用，重点关注开源材料，如 MDPI 2019 和 Vopicka 2014，以支持关于双模式模型在聚合物膜气体吸附中差异和挑战的讨论。

I'm gathering citations, focusing on open-source materials like MDPI 2019 and Vopicka 2014, to support the discussion on differences and challenges in the dual-mode model for gas sorption in polymeric membranes.

我正在组织关于纯气体与混合气体吸附、探索双模式吸附模型以及详细说明挑战（如参数不确定性和混合气体预测）的章节。

I'm organizing sections on pure vs mixed-gas sorption, exploring the dual-mode sorption model, and detailing challenges like parameter uncertainty and mixed gas prediction.

我专注于双模式吸附模型，详细说明纯气体和混合气体吸附行为，并通过项目符号和结构化章节突出关键差异和挑战，以提高清晰度。

I’m focusing on the dual-mode sorption model, detailing pure and mixed-gas sorption behaviors, and highlighting key differences and challenges with bullet points and structured sections for clarity.

好的，让我看看。我依赖[3]、[20]、[22]和[21]来获得对双模式吸附和气体混合物的清晰见解。

OK, let me see. I’m leaning on [3], [20], [22], and [21] for their clear insights into dual-mode sorption and gas mixtures.

我正在拼凑参数名称以避免混淆。坚持使用(k)、(C_H')和(b)以保持清晰。纯气体和混合物的方程已详细说明并格式清晰。

I’m piecing together parameter names to avoid confusion. Sticking with (k), (C_H'), and (b) for clarity. The equations for pure gas and mixture are detailed and clearly formatted.

我正在处理多解参数拟合、聚合物塑化和时间效应。这些复杂性使得预测纯气体和混合气体吸附变得棘手。

I'm tackling multi-solution parameter fits, polymer plasticization, and temporal effects. These intricacies make predicting pure and mixed gas sorption tricky.

我正在构建关于吸附差异、纯气体双模式模型、其扩展到混合气体以及相关挑战的章节。这种递进看起来合乎逻辑且有效。

I’m structuring sections on sorption differences, the dual-mode model for pure gases, its extension to mixed gases, and the associated challenges. This progression seems logical and effective.

按估计经济价值划分的专家级任务通过率

Pass Rate on Expert-Level Tasks by Estimated Economic Value

按估计小时数划分的专家级任务通过率

Pass Rate on Expert-Level Tasks by Estimated Hours

任务的估计经济价值与通过率的相关性高于人类所需小时数——模型认为困难的事情与人类认为耗时的事情不同。

Estimated economic value of task is more correlated with pass rate than # of hours it would take a human – the things that models find difficult are different to what humans find time-consuming.

局限性 Limitations

深度研究解锁了重要的新能力，但仍处于早期阶段且存在局限性。根据内部评估，它有时会在回复中虚构事实或做出错误推断，尽管发生率明显低于现有的 ChatGPT 模型。它可能难以区分权威信息与谣言，目前在置信度校准方面表现较弱，往往无法准确传达不确定性。发布时，报告和引用中可能存在轻微格式错误，任务启动也可能需要更长时间。我们预计随着更多使用和时间的推移，这些问题将迅速改善。

Deep research unlocks significant new capabilities, but it’s still early and has limitations. It can sometimes hallucinate facts in responses or make incorrect inferences, though at a notably lower rate than existing ChatGPT models, according to internal evaluations. It may struggle with distinguishing authoritative information from rumors, and currently shows weakness in confidence calibration, often failing to convey uncertainty accurately. At launch, there may be minor formatting errors in reports and citations, and tasks may take longer to kick off. We expect all these issues to quickly improve with more usage and time.

访问权限 Access

ChatGPT 中的深度研究目前计算量非常大。研究一个查询所需的时间越长，所需的推理算力就越多。我们从今天开始推出针对 Pro 用户的优化版本，每月最多可进行 100 次查询。Plus 和 Team 用户将随后获得访问权限，然后是 Enterprise 用户。我们仍在努力为英国、瑞士和欧洲经济区的用户提供访问权限。

Deep research in ChatGPT is currently very compute intensive. The longer it takes to research a query, the more inference compute is required. We are starting with a version optimized for Pro users today, with up to 100 queries per month. Plus and Team users will get access next, followed by Enterprise. We are still working on bringing access to users in the United Kingdom, Switzerland, and the European Economic Area.

所有付费用户很快将获得更高的速率限制，届时我们将发布一个更快、更具成本效益的深度研究版本，该版本由较小的模型驱动，但仍能提供高质量的结果。

All paid users will soon get significantly higher rate limits when we release a faster, more cost-effective version of deep research powered by a smaller model that still provides high quality results.

在接下来的几周和几个月里，我们将致力于技术基础设施，密切监控当前版本，并进行更严格的测试。这符合我们迭代部署的原则。如果所有安全检查继续满足我们的发布标准，我们预计大约一个月后向 Plus 用户发布深度研究。

In the coming weeks and months, we’ll be working on the technical infrastructure, closely monitoring the current release, and conducting even more rigorous testing. This aligns with our principle of iterative deployment. If all safety checks continue to meet our release standards, we anticipate releasing deep research to Plus users in about a month.

未来展望 What's next

深度研究功能现已登陆 ChatGPT 网页版，并将在本月内推广至移动端和桌面应用。目前，深度研究可以访问开放网络和任何上传的文件。未来，你将能够连接到更多专业数据源——扩展其对基于订阅或内部资源的访问——使其输出更加稳健和个性化。

Deep research is available today on ChatGPT web, and will be rolled out to mobile and desktop apps within the month. Currently, deep research can access the open web and any uploaded files. In the future, you’ll be able to connect to more specialized data sources—expanding its access to subscription-based or internal resources—to make its output even more robust and personalized.

展望更远的未来，我们设想在 ChatGPT 中整合智能体式体验，用于异步、真实世界的研究与执行。深度研究能够执行异步在线调查，而 Operator 能够采取真实世界行动，两者的结合将使 ChatGPT 能够为你执行日益复杂的任务。

Looking further ahead, we envision agentic experiences coming together in ChatGPT for asynchronous, real-world research and execution. The combination of deep research, which can perform asynchronous online investigation, and Operator, which can take real-world action, will enable ChatGPT to carry out increasingly sophisticated tasks for you.

__2025 年 2 月 3 日补充__：我们对驱动深度研究的 o3 早期版本进行了严格的安全测试、准备评估和治理审查，将其识别为_中等_⁠(在新窗口中打开)⁠风险。我们还进行了额外的安全测试，以更好地理解与深度研究浏览网页能力相关的增量风险，并增加了新的缓解措施。我们将继续彻底测试并密切监控当前的有限发布。当我们向 Plus 用户扩大访问权限时，我们将在系统卡中分享深度研究的安全见解和保障措施。

_February 3, 2025 addendum__: We conducted rigorous safety testing, preparedness evaluations, and governance reviews on the early version of o3 that powers deep research, identifying it asMedium_⁠(opens in a new window)_risk. We also ran additional safety testing to better understand incremental risks associated with deep research's ability to browse the web, and we have added new mitigations. We will continue to thoroughly test and closely monitor the current limited release. We will share our safety insights and safeguards for deep research in a system card when we widen access to Plus users._