[论文解读] Accelerating Scientific Research with Gemini: Case Studies and Common Techniques

D. P. Woodruff, Vincent Cohen-Addad+34 more|arXiv (Cornell University)|Feb 3, 2026

Machine Learning in Materials Science被引用 2

一句话总结

论文展示了使用 Google Gemini 模型进行人工智能辅助理论研究的案例研究，以解决未解问题、反驳猜想并生成证明，并提炼出协作技术的实用清单。

ABSTRACT

Recent advances in large language models (LLMs) have opened new avenues for accelerating scientific research. While models are increasingly capable of assisting with routine tasks, their ability to contribute to novel, expert-level mathematical discovery is less understood. We present a collection of case studies demonstrating how researchers have successfully collaborated with advanced AI models, specifically Google's Gemini-based models (in particular Gemini Deep Think and its advanced variants), to solve open problems, refute conjectures, and generate new proofs across diverse areas in theoretical computer science, as well as other areas such as economics, optimization, and physics. Based on these experiences, we extract common techniques for effective human-AI collaboration in theoretical research, such as iterative refinement, problem decomposition, and cross-disciplinary knowledge transfer. While the majority of our results stem from this interactive, conversational methodology, we also highlight specific instances that push beyond standard chat interfaces. These include deploying the model as a rigorous adversarial reviewer to detect subtle flaws in existing proofs, and embedding it within a "neuro-symbolic" loop that autonomously writes and executes code to verify complex derivations. Together, these examples highlight the potential of AI not just as a tool for automation, but as a versatile, genuine partner in the creative process of scientific discovery.

研究动机与目标

• 展示先进的人工智能模型如何在理论计算机科学及相关领域中与人类共同 tackling 未解问题的能力。
• 识别并分享在严谨数学推理中实现高效人机协作的可复用技术。
• 展示 AI 在猜想反驳、证明构建和外部验证方面的具体流程。

提出的方法

• 记录使用基于 Gemini 的模型处理未解问题的真实世界协作系列。
• 提取并形式化常见技术，如迭代提示、跨域类比、以及用于反例搜索的仿真。
• 描述神经符号循环中 AI 生成并验证代码以支撑推导的过程。
• 呈现对抗性评审与外部验证工作流以确保严谨性。
• 概述 AI 辅助研究手册及人机协作的动态。

Figure 1 : Overview of the reasoning architecture used in many testimonials: an extensive exploration of the solution space combined with deep reasoning and a long tail of automated and human verification and in several cases, guidance and iterative feedback.

实验结果

研究问题

• RQ1 在结合人类专业知识时，哪些 AI 驱动的工作流能够实现有意义的数学与理论进展？
• RQ2 哪些技术最适合利用 Gemini 模型在猜想检验、证明构建与跨域验证中发挥作用？
• RQ3 AI 是否能够充当对抗性评审者或自治的验证者，以提升证明与文献的严格性？
• RQ4 通过 AI 的跨学科联系如何有助于解决 TCS 及相关领域的未解问题？

主要发现

• 案例研究表明，AI 辅助协作在 TCS、经济学、优化和物理等领域能够产生猜想反驳、新颖证明和更深入的见解。
• 出现了一组可重复的技术：迭代细化、思想跨域融合、仿真与反例搜索、形式化与严格性检查、与外部验证的互动证明构建，以及具备自动反馈的智能工具使用。
• AI 可以作为对抗性评审者并在神经符号循环中编写并执行代码以验证推导。
• 人类引导仍然至关重要；成功关键在于结构化提示、问题分解以及严格的外部验证。
• 研究工作提出了一个实用的 AI 辅助研究手册，并强调了对未来研究工作流的影响。

(a) From Discrete Combinatorics to Continuous Measure Theory: To resolve an open question about bounded-rank SDP solutions for Max-Cut, the AI reframed a discrete combinatorial problem involving unit vectors into an energy minimization problem over continuous probability measures on the unit sphere