Year: 2026
Type: preprint
Abstract: We present an extension and comprehensive real-world validation of Co-Scientist, a Gemini-based multi-agent system designed to accelerate end-to-end scientific research across hypothesis generation, experimentation, and manuscript generation. Moving beyond in silico hypothesis generation, this specialized configuration transitions Co-Scientist into an execution-grounded research partner advancing closed-loop scientific workflows across materials science, biology, and computer science. In materials science, Co-Scientist interfaced with a semi-automated chemical vapor deposition reactor to design a safe precursor route for MXenes; experimental execution produced a lamellar 2D material sharing key structural similarities with the Ti3C2Tx MXene lattice, although further experiments are needed to confirm the atomic structure. Leveraging Gemini 3 Deep Think for rapid, lab-in-the-loop execution, it also tailored growth recipes to laboratory constraints in minutes, enabling single-attempt growth of monolayer MoS2, MoSe2, and WS2 semiconductors. In biology, Co-Scientist predicted emergent swarming phenotypes of engineered E. coli across inducer (IPTG) gradients from sparse imaging data, quantitatively matching unpublished wet-lab morphological measurements. In computer science, Co-Scientist autonomously discovered an inference-time scaling architecture that outperformed six frontier models on HealthBench (Hard and Professional) while reducing potential clinical harm under blinded physician evaluation. Finally, a double-blind study of end-to-end generated papers with 30 domain experts across 450 reviews demonstrates that Co-Scientist's reliability modules reduce hallucination and plagiarism while improving research safety. Together, these results demonstrate progress toward closed-loop multi-agent scientific AI systems capable of accelerating real-world scientific discovery.
Source: arXiv (Cornell University)
Authors: Schmidgall, Samuel, Zhu, Xiaokai, Shaw, Marian, Yang, Lin, Liévin, Valentin, Yang, Jingyun, Zhuang, Yuchen, Strother, Tim, Bijamov, Alex, Sun, Min Woo, Palepu, Anil, Chen, Justin, Steiner, David, Shreibati, Jacqueline, Weng, Wei-Hung, Zhao, Yilin, Hu, Xingjian, Zahn, Nicholas, Garg, Sadhya, Kirby, Julia, Gan, Yuxiang, Li, Jiaoli, Thakkar, Divy, Azizi, Shekoofeh, Racz, David, Gottweis, Juraj, Natarajan, Vivek, Wu, Chenglin, Danino, Tal, Rong, Keran, Wang, Haozhe, Schillings, Benoit, Cheng, Yong, Le, Quoc V., Tu, Tao
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7204557982
Cites:
Cited by:
Related to: