Search papers, labs, and topics across Lattice.
This paper details the real-world application and validation of Co-Scientist, a Gemini-based multi-agent system that enhances scientific research workflows across hypothesis generation, experimentation, and manuscript creation. The system was tested in materials science, biology, and computer science, achieving significant results such as the successful design of a precursor route for MXenes and the autonomous discovery of an architecture that surpassed leading models in inference-time scaling. Notably, a double-blind study showed that Co-Scientist's reliability modules effectively reduced hallucination and plagiarism while improving research safety, marking a significant advancement in closed-loop scientific AI systems.
Co-Scientist not only accelerates scientific discovery but also ensures the reliability of generated research outputs, reducing hallucination and plagiarism in a double-blind study.
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phenotypes of engineered E. coli across inducer (IPTG) gradients from sparse imaging data, quantitatively matching unpublished wet-lab morphological measurements.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.
Google Research