Google Launches AI System to Aid Scientific Research

Artur - stock.adobe.com

Editor's note: this story was originally published on PharmTech.com.

Google has introduced a new artificial intelligence (AI) system designed to help scientists generate novel hypotheses and research proposals, the company announced in a Google Blog post published on Feb. 19, 2025. The new system, AI co-scientist, is a multi-agent AI system that scientists can use to navigate information and insights from scientific publications and other resources.

Built on Gemini 2.0, it is intended to be used as a collaborative tool by scientists and was designed to mirror the reasoning process of the scientific method. The tool can “uncover new, original knowledge [and] formulate demonstrably novel research hypotheses and proposals, building upon prior evidence and tailored to specific research objectives,” according toJuraj Gottweis, Google Fellow, and Vivek Natarajan, Research Lead (1).

AI co-scientist uses a combination of Generation, Reflection, Ranking, Evolution, Proximity, and Meta-review that use automated feedback to “iteratively generate, evaluate, and refine hypotheses, resulting in a self-improving cycle of increasingly high-quality and novel outputs.”It also uses web search and specialized AI models to enhance the quality of the hypotheses. Scientists can interact with the system by directly providing seed ideas or feedback on generated outputs.

The tool analyzes the assigned goal into a research plan configuration that is managed by a supervisor agent that assigns specialized agents and allocates resources. This enables the system to “flexibly scale compute and to iteratively improve its scientific reasoning towards the specified research goal” (1). It then leverages test-time compute scaling to reason, resolve, and improve outputs. It uses self-play-based scientific debate to create novel hypothesis and ranking tournaments for hypothesis comparison. The system self-improves by using the Elo auto-evaluation metric.

“Due to their core role, we assessed whether higher Elo ratings correlate with higher output quality. We analyzed the concordance between Elo auto-ratings and GPQA benchmark accuracy on its diamond set of challenging questions, and we found that higher Elo ratings positively correlate with a higher probability of correct answers. Seven domain experts curated 15 open research goals and best guess solutions in their field of expertise. Using the automated Elo metric we observed that the AI co-scientist outperformed other state-of-the-art agentic and reasoning models for these complex problems. The analysis reproduced the benefits of scaling test-time compute using inductive biases derived from the scientific method. As the system spends more time reasoning and improving, the self-rated quality of results improve and surpass models and unassisted human experts,” Gottweis and Natarajan stated in the blog post (1).

End-to-end laboratory experiments in drug repurposing, proposing novel treatment targets, and elucidating the mechanisms underlying antimicrobial resistance were done using the AI co-scientist to assess the validity of the system’s novel predictions. The tool was used to assist the prediction of drug repurposing to validate predictions through computational biology, expert clinician feedback, and in vitro experiments.

“Notably, the AI co-scientist proposed novel repurposing candidates for acute myeloid leukemia (AML). Subsequent experiments validated these proposals, confirming that the suggested drugs inhibit tumor viability at clinically relevant concentrations in multiple AML cell lines,” Gottweis and Natarajan stated in the blog post (1).

The system does have some limitations and areas of improvement, according to Gottweis and Natarajan, such as enhancing literature reviews, fact-checking, cross-checking with external tools, and larger-scale evaluation with subject matter experts.

“The AI co-scientist represents a promising advance toward AI-assisted technologies for scientists to help accelerate discovery. Its ability to generate novel, testable hypotheses across diverse scientific and biomedical domains—some already validated experimentally—and its capacity for recursive self-improvement with increased compute, demonstrate its potential to accelerate scientists' efforts to address grand challenges in science and medicine. We look forward to responsible exploration of the potential of the AI co-scientist as an assistive tool for scientists. This project illustrates how collaborative and human-centered AI systems might be able to augment human ingenuity and accelerate scientific discovery,” Gottweis and Natarajan stated in the blog post (1).

Reference

1. Gottweis, J. and Natarajan, V. Accelerating Scientific Breakthroughs with AI Co-Scientist. Blog Post. Google Research. Reasearchgoogle. Feb. 19, 2025. https://research.google/blog/accelerating-scientific-breakthroughs-with-an-ai-co-scientist/