Accelerating Scientific Research with Gemini: Case Studies and Common Techniques
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.
Cite
@article{arxiv.2602.03837,
title = {Accelerating Scientific Research with Gemini: Case Studies and Common Techniques},
author = {David P. Woodruff and Vincent Cohen-Addad and Lalit Jain and Jieming Mao and Song Zuo and MohammadHossein Bateni and Simina Branzei and Michael P. Brenner and Lin Chen and Ying Feng and Lance Fortnow and Gang Fu and Ziyi Guan and Zahra Hadizadeh and Mohammad T. Hajiaghayi and Mahdi JafariRaviz and Adel Javanmard and Karthik C. S. and Ken-ichi Kawarabayashi and Ravi Kumar and Silvio Lattanzi and Euiwoong Lee and Yi Li and Ioannis Panageas and Dimitris Paparas and Benjamin Przybocki and Bernardo Subercaseaux and Ola Svensson and Shayan Taherijam and Xuan Wu and Eylon Yogev and Morteza Zadimoghaddam and Samson Zhou and Yossi Matias and James Manyika and Vahab Mirrokni},
journal= {arXiv preprint arXiv:2602.03837},
year = {2026}
}
Comments
The changes over version 2 are that we cleaned up the last paragraph on color-coding at the end of section 2. Also, for section 6.1 we added a reference to followup work of the authors, and other minor edits in that section