Google 推出 Gemini 辅助论文反馈工具

原标题:Gemini-backed Paper Assistant Tool provides automated feedback for theoretical computer scientists at STOC 2026
45AI 研判分

Google Research 宣布在 STOC 2026 会议中部署基于 Gemini 的自动化论文反馈助手,旨在为理论计算机科学领域的研究者提供初步评审意见。该工具目前处于特定学术会议的试点应用阶段,主要聚焦于提升同行评审的效率与覆盖面。

报道正文

本文目录24 个章节

跳至主要内容

探索我们的众多研究领域

浏览所有研究领域

应用 AI 与科学

Image 1: earth_AI_nav 地球 AIImage 2: health_AI_nav 健康 AIImage 3: science_AI_nav 科学 AIImage 4: sustainability_crisis_resilience_nav 可持续性与危机韧性

基础机器学习与算法

Image 5: algorithms_theory_nav 算法与理论Image 6: information_retrieval_nav 信息检索Image 7: machine_intelligence_nav 机器智能Image 8: machine_perception_nav 机器感知Image 9: NLP_nav 自然语言处理

人、系统与量子 AI

Image 10: human_computer_interaction_nav 人机交互与可视化Image 11: networking_nav 网络Image 12: quantum_AI_nav 量子 AIImage 13: responsible_AI_nav 负责任的 AIImage 14: anti_abuse_nav 反滥用Image 15: software_engineering_nav 软件工程Image 16: software_systems_nav1 软件系统

了解更多

Image 17: publications_nav 出版物Image 18: projects_nav 项目

构建协作生态系统

Image 19: dataset_nav 数据集 获取高质量数据集,加速您的研究。Image 20: models_products_nav 工具与服务 探索我们最新的 AI 模型和产品。

Image 21: software_engineering_nav 开源项目 发现开源代码,与社区协作。

共同塑造未来

查看所有项目

Image 22: faculty_programs_nav 教师合作项目 通过与高校教师的深度交流,积极参与学术研究社区。Image 23: student_programs_nav 学生支持项目 通过多样化的活动计划,培养下一代研究人员。

Image 24: R&D-programs_nav_f 研发项目 与业界及学术专家合作,推动基础科学与创新。Image 25: locations_nav 全球布局 在我们的全球办公室和研究实验室中找到你的位置。

将科学发现转化为现实世界的影响

Image 26: earth_AI_nav 人才团队 我们的研究人员通过基础与应用研究,推动计算机科学的发展。

Image 27: teams_nav 研究团队 协作团队致力于解决世界上最棘手的 AI 难题。

研究

探索我们多元化的研究领域

浏览所有研究领域

应用 AI 与科学

Image 28: earth_AI_nav Earth AIImage 29: health_AI_nav Health AIImage 30: science_AI_nav Science AIImage 31: sustainability_crisis_resilience_nav Sustainability & crisis resilience

Foundational ML & algorithms

Image 32: algorithms_theory_nav Algorithms & theoryImage 33: information_retrieval_nav Information retrievalImage 34: machine_intelligence_nav Machine intelligenceImage 35: machine_perception_nav Machine perceptionImage 36: NLP_nav Natural language processing

People, systems & quantum AI

[注:本文篇幅超长,以上为核心前篇精译,后续内容保留原文呈现]

Image 37: human_computer_interaction_nav Human-computer interaction and visualizationImage 38: networking_nav NetworkingImage 39: quantum_AI_nav Quantum AIImage 40: responsible_AI_nav Responsible AIImage 41: anti_abuse_nav Anti abuseImage 42: software_engineering_nav Software engineeringImage 43: software_systems_nav1 Software systems

Learn More

Image 44: publications_nav PublicationsImage 45: projects_nav Projects

Resources

Building a collaborative ecosystem

Image 46: dataset_nav Datasets Access high-quality datasets to accelerate your research.Image 47: models_products_nav Tools & services Explore our latest AI models and products.Image 48: software_engineering_nav Open source Discover open-source code and collaborate with the community.

Conferences & events

Careers

Shaping the future together

See all programs

Image 49: faculty_programs_nav Faculty programs Participating in the academic research community through meaningful engagement with university faculty.Image 50: student_programs_nav Student programs Supporting the next generation of researchers through a wide range of programming.Image 51: R&D-programs_nav_f R&D programs Collaborating with industry and academic experts to support foundational science and innovation.Image 52: locations_nav Locations Find your place in our global offices and research labs.

Blog

About

Translating discovery into real-world impact

Image 53: earth_AI_nav People Our researchers drive advancements in computer science through both fundamental and applied research.Image 54: teams_nav Teams Collaborative groups tackling the world's most challenging AI problems.

Google Research

Google AI Learn about all our AIGoogle DeepMind Explore the frontier of AIGoogle Labs Try our AI experiments

Research

Resources

Conferences & events

Careers

Blog

About

Search

Image 55: The Gemini logo floats above a tablet, surrounded by documents marked with green checkmarks and red X's to symbolize AI evaluation.

  1. Home
  2. Blog

Gemini-backed Paper Assistant Tool provides automated feedback for theoretical computer scientists at STOC 2026

December 15, 2025

Vincent Cohen-Addad and David Woodruff, Research Scientists, Google Research, on behalf of the research team

Update • may 18, 2026

This post has been updated to include the newly released system name, Paper Assistant Tool.

We describe the new Paper Assistant Tool that uses Gemini to help scientists rigorously verify the correctness of their conference submission papers, which was tested for the STOC 2026 conference.

The pursuit of truth in theoretical computer science and mathematics relies on the highest standards of proof, rigor, and clarity. While peer review is the crucial final check, the process of drafting and refining complex theoretical work often takes months, with simple errors, inconsistent variables, or subtle logical gaps frequently slowing down the entire research pipeline. But could a highly specialized AI tool act as a fast, rigorous collaborator, helping authors pre-vet their work before it ever reaches human reviewers?

To test this potential, we created an experimental program for the Annual ACM Symposium on Theory of Computing (STOC 2026) — one of the most prestigious venues in theoretical computer science. This program offered authors automated, pre-submission feedback generated by a specialized Gemini AI tool now known as Paper Assistant Tool (PAT). Our objective was to provide constructive suggestions and identify potential technical issues within 24 hours of submission, helping authors polish their final drafts before the submission deadline.

The responses were very positive: PAT successfully identified a variety of issues, including calculation and logic errors. Here we report how we developed the tool and the results of its use.

Optimized for mathematical rigor

The feedback tool leveraged inference scaling methods in an advanced version of Gemini 2.5 Deep Think. This setup enables PAT to simultaneously explore and combine multiple possible solutions before giving a final answer, rather than pursuing a single, linear chain of thought. By combining different reasoning and evaluation traces, the method reduces inherent hallucinations and focuses on the most salient issues.

Feedback format

Authors received structured feedback divided into key sections: a summary of the paper's contributions, a list of potential mistakes and improvements (often analyzing specific lemmas or theorems), and a list of minor corrections and typos. See some feedback examples.

Impact and technical depth

PAT successfully identified a wide range of issues, from inconsistent variable names to complex problems like calculation errors, incorrect application of inequalities, and logical gaps in proofs. As one author noted, the tool found "a critical bug... that made our proof entirely incorrect," further adding that it was an "embarrassingly simple bug that evaded us for months."

Over 100 participants responded to our post-experiment survey and the responses were very positive, with individuals citing the model’s success at finding critical errors and its ability to return insightful commentary. Of those who gave us consent to publish their feedback:

  • 80% of submitted papers at the time our experiment ended had opted-in for our AI review

  • 97% found the feedback helpful
  • 97% would use this tool again for future submissions
  • 81% found PAT improved clarity or readability of the paper

Image 56: Three testimonials from university professors praising the tool for identifying significant errors and bugs in their research papers.

The user experience

Beyond technical accuracy, authors valued the speed and neutrality of the AI review. Participants noted receiving feedback in just two days. Others praised the "neutral tone and rigor" of the output, finding it a useful complement to human readers.

Image 57: A testimonial graphic from Professor Shuchi Chawla praising the tool for providing valuable feedback that exceeded expectations.

Interpreting PAT's output

Because participants are experts in their respective fields, they were able to readily distinguish helpful insights from occasional "hallucinations". While the model sometimes struggled — particularly with parsing complex notation or interpreting figures — authors weren't dismissive of the LLM's output. Rather, they carefully filtered out the noise and extracted the important and correct parts of the output, and then used the feedback as a starting point for verification. This outcome clearly demonstrates the potential for AI to serve as a collaborative partner, augmenting the research workflow by helping human experts to make informed decisions based on the model's rigorous outputs.

Educational impact and future outlook

The research community surveyed in this experiment saw significant potential for this tool in training the next generation. 75% of surveyed authors believed PAT has educational value for students by offering immediate feedback on mathematical rigor and presentation clarity.

This pilot demonstrated the potential for specialized AI tools to serve as collaborative partners in fundamental areas, establishing a target for potential future research initiatives. Our overall goal is not to replace the critical peer review process, but rather to augment and enhance it. Reflecting this, 88% of participants expressed strong interest in having continuous access to such a tool throughout their entire research process.

Acknowledgements

Vincent Cohen-Addad, Rajesh Jayaram, Jon Schneider, and David Woodruff co-led the Paper Assistant Tool project, with key contributions by Lalit Jain, Jieming Mao, and Vahab Mirrokni. We also thank the STOC 2026 PC chair Artur Czumaj and the many other authors who participated in this experiment and provided their valuable feedback, helpful suggestions, and discussions, including Mohammad Taghi Hajiaghayi, Ravi Kumar, Yossi Matias, and Sergei Vassilvitskii. Finally, this work builds on the efforts of the Deep Think team: Garrett Bingham, Irene Cai, Heng-Tze Cheng, Yong Cheng, Kristen Chiafullo, Vincent Cohen-Addad, Paul Covington, Golnaz Ghiasi, Chenjie Gu, Huan Gui, Ana Hosseini, Dawsen Hwang, Lalit Jain, Vihan Jain, Ragha Kotikalapudi, Chenkai Kuang, Chenkai Kuang, Maciej Kula, Nate Kushman, Jane Labanowski, Quoc Le, Jonathan Lee, Zhaoqi Leng, Steve Li, YaGuang Li, Hanzhao (Maggie) Lin, Evan Liu, Yuan Liu, Thang Luong, Jieming Mao, Vahab Mirrokni, Pol Moreno, Nigamaa Nayakanti, Aroonalok Pyne, Shubha Raghvendra, Sashank Reddi, Nikunj Saunshi, Siamak Shakeri, Archit Sharma, Xinying Song, Qijun Tan, Yi Tay, Trieu Trinh, Theophane Weber, Winnie Xu, Zicheng Xu, Shunyu Yao, Lijun Yu, Hao Zhou, Honglei Zhuang, and Song Zuo.


  1. The authors of this blog post and all team members are listed in alphabetical order.

×❮❯

Image 61: STOC-2-Quotes2

Three testimonials from university professors praising the tool for identifying significant errors and bugs in their research papers.

Image 62: STOC-1-Quotes2

A testimonial graphic from Professor Shuchi Chawla praising the tool for providing valuable feedback that exceeded expectations.

Follow us

Explore our other initiatives

Google AI

Discover how Google AI is committed to enriching knowledge and solving complex challenges

Google Cloud

High-performance infrastructure for cloud computing, data analytics & machine learning

Google DeepMind

Our mission is to build AI responsibly to benefit humanity

Google Labs

Explore the future of AI responsibly with Google Labs

About Google

Google Products

Privacy

Terms

Cookies management controls

×

Image 63