Google 推出 Gemini 辅助论文反馈工具
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
探索我们的众多研究领域
应用 AI 与科学
基础机器学习与算法
人、系统与量子 AI
人机交互与可视化
网络
量子 AI
负责任的 AI
反滥用
软件工程
软件系统
了解更多
构建协作生态系统
数据集 获取高质量数据集,加速您的研究。
工具与服务 探索我们最新的 AI 模型和产品。
共同塑造未来
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。
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。
研发项目 与业界及学术专家合作,推动基础科学与创新。
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
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。
研究
探索我们多元化的研究领域
应用 AI 与科学
Earth AI
Health AI
Science AI
Sustainability & crisis resilience
Foundational ML & algorithms
Algorithms & theory
Information retrieval
Machine intelligence
Machine perception
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]
Human-computer interaction and visualization
Networking
Quantum AI
Responsible AI
Anti abuse
Software engineering
Software systems
Learn More
Resources
Building a collaborative ecosystem
Datasets Access high-quality datasets to accelerate your research.
Tools & services Explore our latest AI models and products.
Open source Discover open-source code and collaborate with the community.
Careers
Shaping the future together
Faculty programs Participating in the academic research community through meaningful engagement with university faculty.
Student programs Supporting the next generation of researchers through a wide range of programming.
R&D programs Collaborating with industry and academic experts to support foundational science and innovation.
Locations Find your place in our global offices and research labs.
About
Translating discovery into real-world impact
People Our researchers drive advancements in computer science through both fundamental and applied research.
Teams Collaborative groups tackling the world's most challenging AI problems.
Google AI Learn about all our AIGoogle DeepMind Explore the frontier of AIGoogle Labs Try our AI experiments
Research
Resources
Careers
About
Search

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.
Quick links
-
Share
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

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.

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.
- The authors of this blog post and all team members are listed in alphabetical order.
Quick links
-
Share
Other posts of interest
October 5, 2026 Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle * Generative AI · * Natural Language Processing · * Security, Privacy and Abuse Prevention
September 29, 2026 How Diffusion Controller unifies and simplifies AI image generation * Algorithms & Theory · * Machine Intelligence
September 24, 2026 Automating coherent long-form video generation * Generative AI · * Machine Intelligence
×❮❯

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

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
Cookies management controls
×