_version_ 1866915839031115776
author Woodruff, David P.
Cohen-Addad, Vincent
Jain, Lalit
Mao, Jieming
Zuo, Song
Bateni, MohammadHossein
Branzei, Simina
Brenner, Michael P.
Chen, Lin
Feng, Ying
Fortnow, Lance
Fu, Gang
Guan, Ziyi
Hadizadeh, Zahra
Hajiaghayi, Mohammad T.
JafariRaviz, Mahdi
Javanmard, Adel
S., Karthik C.
Kawarabayashi, Ken-ichi
Kumar, Ravi
Lattanzi, Silvio
Lee, Euiwoong
Li, Yi
Panageas, Ioannis
Paparas, Dimitris
Przybocki, Benjamin
Subercaseaux, Bernardo
Svensson, Ola
Taherijam, Shayan
Wu, Xuan
Yogev, Eylon
Zadimoghaddam, Morteza
Zhou, Samson
Matias, Yossi
Manyika, James
Mirrokni, Vahab
author_facet Woodruff, David P.
Cohen-Addad, Vincent
Jain, Lalit
Mao, Jieming
Zuo, Song
Bateni, MohammadHossein
Branzei, Simina
Brenner, Michael P.
Chen, Lin
Feng, Ying
Fortnow, Lance
Fu, Gang
Guan, Ziyi
Hadizadeh, Zahra
Hajiaghayi, Mohammad T.
JafariRaviz, Mahdi
Javanmard, Adel
S., Karthik C.
Kawarabayashi, Ken-ichi
Kumar, Ravi
Lattanzi, Silvio
Lee, Euiwoong
Li, Yi
Panageas, Ioannis
Paparas, Dimitris
Przybocki, Benjamin
Subercaseaux, Bernardo
Svensson, Ola
Taherijam, Shayan
Wu, Xuan
Yogev, Eylon
Zadimoghaddam, Morteza
Zhou, Samson
Matias, Yossi
Manyika, James
Mirrokni, Vahab
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03837
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Accelerating Scientific Research with Gemini: Case Studies and Common Techniques
Woodruff, David P.
Cohen-Addad, Vincent
Jain, Lalit
Mao, Jieming
Zuo, Song
Bateni, MohammadHossein
Branzei, Simina
Brenner, Michael P.
Chen, Lin
Feng, Ying
Fortnow, Lance
Fu, Gang
Guan, Ziyi
Hadizadeh, Zahra
Hajiaghayi, Mohammad T.
JafariRaviz, Mahdi
Javanmard, Adel
S., Karthik C.
Kawarabayashi, Ken-ichi
Kumar, Ravi
Lattanzi, Silvio
Lee, Euiwoong
Li, Yi
Panageas, Ioannis
Paparas, Dimitris
Przybocki, Benjamin
Subercaseaux, Bernardo
Svensson, Ola
Taherijam, Shayan
Wu, Xuan
Yogev, Eylon
Zadimoghaddam, Morteza
Zhou, Samson
Matias, Yossi
Manyika, James
Mirrokni, Vahab
Computation and Language
Artificial Intelligence
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.
title Accelerating Scientific Research with Gemini: Case Studies and Common Techniques
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2602.03837