Google 发布 Deep Review，面向全球开放技术文档自动评审

生成式AI加速了许多技术领域的发展。如今，AI在撰写科学论文和技术文档、运行代码、设计实验以及起草提案中发挥一定作用已很常见。然而，内容创作的加速带来了评审挑战：在AI生成内容快速增加的同时，人类的验证能力基本保持不变。评审长篇科学手稿或复杂法律协议等复杂文档需要专业知识和深厚的学科背景。这种失衡造成了验证瓶颈，即信息生成的速度超过了对其进行严格评审的速度。

Generative AI has accelerated many technical fields. It is now common for AI to play some role in writing scientific papers and technical documents, running code, designing experiments, and drafting proposals. However, accelerating content creation has created a review challenge: the human capacity for verification has remained largely fixed amid this rapid increase in AI-generated content. Reviewing complex documents like long scientific manuscripts or complex legal agreements requires specialized expertise and advanced subject knowledge. This imbalance creates a validation bottleneck, where information is being generated faster than it can be rigorously reviewed.

今天，我们很高兴宣布Deep Review正式公开发布。这是一个智能体AI系统，旨在为复杂文档提供严谨的反馈和技术验证。该系统最初为计算机科学学术论文分析而设计，如今其能力已扩展到评审法律、金融等多个领域的文档。它既可在起草过程中作为迭代改进工具使用，也可在评审过程中用于科学流程验证、主张核查和评估。

Today, we’re excited to announce the public release of Deep Review, an agentic AI system engineered to provide rigorous feedback and technical verification on complex documents. Initially designed for computer science academic paper analysis, the system’s capabilities have expanded to review documents across many domains, such as legal and finance. It can be used as both an iterative improvement tool during the drafting process and a tool for the scientific process verification, claims, and evaluation during the review process.

Deep Review代表了我们Paper Assistant Tool（PAT）的演进。PAT是一项实验性计划，旨在帮助研究人员在会议投稿前对手稿进行压力测试。过去一年中，我们与四个旗舰计算机科学会议（STOC 2026、ICML 2026、NeurIPS 2026、和ICLR 2027）合作，为超过16,000份选择参与的手稿作者提供私密的投稿前反馈。有关PAT及这些试点项目的更多细节，请参阅我们的手稿Towards Automating Scientific Review with Google’s Paper Assistant Tool。

Deep Review represents the evolution of our Paper Assistant Tool (PAT) — an experimental initiative developed to help researchers stress-test manuscripts prior to conference submission. Over the past year, we partnered with four flagship computer science conferences (STOC 2026, ICML 2026, NeurIPS 2026, and ICLR 2027) to provide private, pre-submission feedback to authors of more than 16,000 manuscripts who opted in. Further details on PAT and these pilots can be found in our manuscript, Towards Automating Scientific Review with Google’s Paper Assistant Tool.

通过此次发布，Deep Review现已面向全球开放：

With this release, Deep Review is now accessible worldwide:

• 分级访问与可扩展API：每位用户每周可获得两次免费文档评审。有大批量工作流程需求的用户可连接其Gemini API密钥，以获得更高的使用限额，并通过Deep Review API进行程序化集成。
• 格式灵活性：Deep Review初期支持PDF和纯文本作为输入格式，多文件输入支持即将推出。
• 隐私与数据政策：上传至Deep Review的文档绝不会用于训练、微调或改进Google模型。上传的文档将保存一年，唯一目的是在Deep Review界面中向用户展示。

• Tiered access and scalable API: Every user receives two complimentary document reviews per week. Users with high-volume workflows can connect their Gemini API key for higher usage limits and programmatic integration via the Deep Review API.
• Format flexibility: Deep Review will initially support PDFs and plain text as input formats, with support for multi-file inputs coming soon.
• Privacy and data policy: Documents uploaded to Deep Review are never used to train, fine-tune, or improve Google models. Uploaded documents are stored for one year for the sole purpose of display to the user in the Deep Review UI.

Deep Review加速技术验证

Deep Review accelerates technical validation

验证瓶颈最显著的例子之一是学术同行评审。这体现在学术出版场所投稿量的上升，尤其是AI研究自身的会议，投稿量出现了急剧增长。今年，三大AI会议（ICLR、NeurIPS和ICML）的投稿量超过74,000篇，高于2025年的约45,000篇、2024年的32,000篇和2023年的23,000篇。每篇投稿都需要多份高质量评审以确保同行评审流程的完整性，这可能会给人类专家带来更大的负担。

One of the most significant examples of the validation bottleneck is in academic peer review. This can be seen in the uptick of submissions to academic publication venues, especially venues for AI research itself, which have seen a dramatic rise. This year, there were over 74,000 submissions to three major AI conferences (ICLR, NeurIPS, and ICML) up from approximately 45,000 in 2025, 32,000 in 2024, and 23,000 in 2023. Each of these submissions requires multiple high-quality reviews to ensure the integrity of the peer review process, which can place a larger burden on human experts.

Deep Review 旨在帮助减轻技术领域人类审稿人日益加重的负担。通过对文档提供详细、客观的评估，Deep Review 检查逻辑一致性和数学陈述，提出改进建议，核实事实依据，并与现有工作进行对比。它处理审稿中一些认知负担最重的环节，同时将更高层次的判断留给人类。

Deep Review aims to help alleviate this expanding burden on human reviewers across technical fields. By providing detailed, objective evaluations of documents, Deep Review checks logical consistency and mathematical statements, suggests improvements, grounds facts, and compares with existing work. It addresses some of the most cognitively burdensome facets of review, while leaving higher-level judgements to humans.

经过验证的科学审稿记录

A proven track record for scientific review

Deep Review 已以其实验名称 Paper Assistant Tool（PAT）进行了广泛测试和部署，与旗舰计算机科学会议 STOC 2026、ICML 2026、NeurIPS 2026 和 ICLR 2027 开展了四项试点合作。在这些试点期间，作者可以在提交截止日期前几周选择通过 PAT 获得对其论文的反馈和分析。目标是向作者提供可操作的反馈，帮助提高提交论文的质量。这些反馈与官方会议审稿流程完全脱钩。PAT 未收集任何数据用于训练，且在每个项目结束后，论文会立即从 Google 系统中删除。

Deep Review has been extensively tested and deployed under its experimental name, the Paper Assistant Tool (PAT), in four pilot partnerships with the flagship computer science conferences STOC 2026, ICML 2026, NeurIPS 2026, and ICLR 2027. During these pilots, authors were able to opt-in to receive feedback and analysis on their paper via PAT in the weeks before the submission deadline. The goal was to provide authors with actionable feedback to help improve the quality of papers in submission. This feedback was completely decoupled from the official conference review process. PAT did not collect any of the data for training, and papers were deleted from Google systems promptly after each program concluded.

作者对该工具的反应非常积极，这反映了底层模型和 PAT 框架的持续改进。随着 Deep Review 中加入 Gemini 4 Argon 支持，该工具的底层能力已进一步超越下文所述的旧版 PAT。

Author reactions to the tool have been extremely positive, and reflect continued improvements to both underlying models and the PAT harness. With the addition of Gemini 4 Argon support in Deep Review, the underlying capabilities of the tool have further increased beyond the older iterations of PAT described below.

Deep Review 的工作原理

How Deep Review works

单提示词 LLM 调用在评估长篇复杂文档时常常失败，原因包括耗尽 token 推理预算、忽略长上下文中的跨章节依赖关系，或未经充分审查就接受细微的论断。Deep Review 通过四阶段智能体流水线解决这些挑战：

Single-prompt LLM calls often fail when evaluating long, complex documents due to exhausting their token reasoning budget, overlooking long-context cross-section dependencies, or accepting nuanced claims without fully scrutinizing them. Deep Review solves these challenges through a four-stage agentic pipeline:

1. 文档分段：文档首先被摄入，并由分段智能体自主分解为逻辑段落（例如引言、实验、方法等）。这些段落可以重叠，且必须覆盖输入文档的全部内容。
2. 自适应预算：并非所有章节都需要相同的认知深度。流水线会检查信息密度并动态分配计算预算，同时为每个章节配备专门的推理扩展流水线。例如，包含密集数学证明的章节可能比学术论文的引言或相关工作章节获得更多计算资源。
3. 深度并行验证：专门的推理智能体并行审查每个段落。每个智能体都可以访问完整文档上下文以追踪交叉引用，但将其推理能力专门集中于审查其特定目标段落的任务。这既确保每个审查集群的审查任务可控，又确保并行集群得到适当协调。
4. 全局综合与智能体事实核查：专门的综合智能体整合段落级报告，并在章节之间进行最终一致性检查，必要时重新运行逻辑检查。该智能体还执行外部事实核查和工具调用，作为防止幻觉的最终预防措施。

1. Document segmentation: The document is first ingested and autonomously decomposed by a segmenter agent into logical segments (e.g., Introduction, experiments, methodology, etc.). These segments can be overlapping, and must cover all the content of the input document.
2. Adaptive budgeting: Not all sections require equal cognitive depth. The pipeline inspects information density and dynamically allocates a compute budget, along with a specialized inference scaling pipeline for each section. For instance, sections with dense mathematical proofs may receive more compute than an introduction or a related work section in an academic paper.
3. Deep parallel verification: Specialized reasoning agents scrutinize each segment in parallel. Each agent has access to the full document context to track cross-references, but focuses its reasoning power specifically on the task of reviewing its specific target section. This ensures both that reviewing tasks are manageable for each review swarm, and that parallel swarms are properly coordinated.
4. Global synthesis and agentic grounding: A dedicated synthesis agent consolidates the segment-level reports, and does final consistency checks between sections, rerunning logical checks if required. The agent further performs external grounding checks and tool calls as a final preventative measure against hallucinations.

通用验证与审稿：超越研究论文

Universal verification and review: Beyond research papers

虽然 Deep Review 起源于学术论文评审，但长上下文评审具有可推广性：用于检查研究论文中数学证明是否成立的推理机制，同样有助于发现其他类型文档中的逻辑漏洞和不一致之处——在这些文档中，主张必须有证据支撑。因此，Deep Review 可用于为更广泛的日常流程带来结构化评审。

While Deep Review originated in academic paper reviews, long-context review is generalizable: reasoning mechanisms used to check whether a mathematical proof holds up in a research paper can also help surface logical gaps and inconsistencies in other types of documents, where claims must be backed by evidence. Therefore, Deep Review can be used to bring structured critique to a broader range of everyday workflows.

用户现在可以在众多领域应用 Deep Review 来分析复杂文档。例如，它可以用于：

Users can now apply Deep Review to analyze complex documents across many domains. For instance, it can be run on:

• 设计文档：发现未明说的架构假设，找出边缘情况，并提出具体改进建议。
• 演示文稿：确保幻灯片之间的过渡逻辑流畅，并确保要点与可视化图表相符。
• 法律和财务文档：检查各条款和数据表之间的内部一致性，标记含糊的术语或下游后果，并让主张有支撑证据作为依据。

• Design documents: Catch unstated architectural assumptions, spot edge cases, and suggest concrete improvements.
• Presentations: Ensure slide transitions flow logically and bulleted takeaways match visual charts.
• Legal and financial documents: Check internal consistency across clauses and data tables, flag ambiguous terms or downstream consequences, and ground claims against supporting evidence.

Deep Review 与 Antigravity 结合

Deep Review meets Antigravity

我们还推出了 Teamwork Deep Document Review Pattern，这是一种受 Deep Review 启发的文档评审实现模式，已使用 Teamwork 多智能体编排框架内置于 Antigravity 中。该模式旨在系统性地评估研究论文、稿件草稿和技术提案，采用带自我纠正和基于分段的评分标准的多智能体层级结构。Antigravity 用户可以使用 /teamwork-preview 命令调用此模式。

We’re also introducing the Teamwork Deep Document Review Pattern, a document review implementation pattern inspired by Deep Review built into Antigravity using the Teamwork multi-agent orchestration framework. This pattern is designed systematically to evaluate research papers, manuscript drafts, and technical proposals using a multi-agent hierarchy with self-correction and segment-based rubrics. Antigravity users can invoke this pattern using the /teamwork-preview command.

让全面、高质量的技术评审广泛可及

Making thorough, high-quality technical reviews widely accessible

在计算机科学领域，全面的提交前评审通常依赖于广泛的评审网络——如资深教师、资源充足的学术实验室或广泛的同行咨询网络。提供可靠的自动化逻辑验证，可以帮助许多学者对自己的论断进行压力测试，发现可避免的缺陷，基于经过验证的基础来完善和强化文档，并更有信心地在评审流程中展示自己的工作。

Comprehensive pre-submission critique in computer science has generally depended on access to extensive review networks — like senior faculty, well-resourced academic laboratories, or extensive peer advisory networks. Providing reliable, automated logical verification can help many academics stress-test their assertions, identify avoidable flaws, refine and strengthen their documents based on verified foundations, and present their work in a review process with more confidence.

开始使用

Get started

我们邀请各地的研究人员、工程师和创作者探索 Deep Review：

We invite researchers, engineers, and creators everywhere to explore Deep Review:

• 试用 Deep Review：访问 Google Research Portal 来评审您的第一批文档。
• 与 API 集成：使用您的 Gemini API key，在持续集成和起草流程中实现程序化验证。
• 阅读研究：阅读预印本，了解底层方法和试点评估。

• Try Deep Review: Visit the Google Research Portal to review your first documents.
• Integrate with the API: Access programmatic verification in your continuous integration and drafting workflows using your Gemini API key.
• Read the research: Read the preprint to explore the underlying methodology and pilot evaluations.

结论与展望

Conclusion and looking ahead

鉴于 Deep Review 在我们与学术会议开展的试点项目中展现出的实用性，我们相信，像 Deep Review 这样的工具将在未来几年通过赋能作者和评审者，在同行评审流程中发挥重要作用。

Given the utility it demonstrated during our pilot programs with academic conferences, we believe that tools like Deep Review will play a significant role across the peer review process in the coming years by empowering both authors and reviewers.

展望未来，我们将继续扩展该平台的能力。随着 Gemini 4 Argon 支持的推出，Deep Review 的底层能力进一步提升，为作者提供更高质量的反馈和分析。此外，随着多文件支持即将推出，用户还将能够同时对整套相关文档、电子表格和附件运行这些相同的一致性检查。我们希望这些进步能让各地知识工作者更广泛地获得高质量的技术评审。

Moving forward, we are continuing to expand the platform’s capabilities. With the rollout of Gemini 4 Argon support, Deep Review’s underlying capabilities further improve, delivering even higher quality feedback and analysis to authors. Additionally, with multi-file support coming soon, users will also be able to run these same consistency checks across entire sets of related documents, spreadsheets, and exhibits simultaneously. We hope these advancements will make high-quality technical reviews more widely accessible for knowledge workers everywhere.

致谢

Acknowledgments

Deep Review 是 Google Research、Google DeepMind 和 Google Cloud 的协作成果。我们感谢核心贡献者和研究合作者——Santiago Balseiro、Taylan Cemgil、Tommaso D'Orsi、Kirk Draheim、Lindi Emoungu、Ayse Erduran、Palash Goyal、Caroline Hartnell、Shobana Kannan、Amy Keeling、Siyi Kou、Bridget Lee、Ian Li、Anoushka Mazumdar、Taylor Montgomery、Mouad Naciri、Uche Okonkwo、Mihir Parmar、Anthony Phalen、Rory Pilgrim、Sarah Presotto Post、Rob Tierney、Drew Tyler、Vishnu V.、Vahab Mirrokni、Laura Vardoulakis、Johannes Welbl、David Woodruff、Yunhan Xu、Jinsung Yoon——以及我们的执行发起人 Katherine Chou、Corinna Cortes、Burak Gokturk、Vahab Mirrokni、Tomas Pfister、Yossi Matias，还有 STOC、ICML、NeurIPS 和 ICLR 的程序主席，感谢他们的合作。

Deep Review is a collaborative effort across Google Research, Google DeepMind, and Google Cloud. We thank our core contributors and research collaborators — Santiago Balseiro, Taylan Cemgil, Tommaso D'Orsi, Kirk Draheim, Lindi Emoungu, Ayse Erduran, Palash Goyal, Caroline Hartnell, Shobana Kannan, Amy Keeling, Siyi Kou, Bridget Lee, Ian Li, Anoushka Mazumdar, Taylor Montgomery, Mouad Naciri, Uche Okonkwo, Mihir Parmar, Anthony Phalen, Rory Pilgrim, Sarah Presotto Post, Rob Tierney, Drew Tyler, Vishnu V., Vahab Mirrokni, Laura Vardoulakis, Johannes Welbl, David Woodruff, Yunhan Xu, Jinsung Yoon — as well as our executive sponsors Katherine Chou, Corinna Cortes, Burak Gokturk, Vahab Mirrokni, Tomas Pfister, Yossi Matias and the Program Chairs of STOC, ICML, NeurIPS, and ICLR for their partnership.

注意转载授权 · 阅读原文。中文正文为 AI 翻译，请以原文为准。

注意转载授权 · 阅读原文