Alphabet’s Google has unveiled an AI agent that it says will aid scientists and researchers in their quest to uncover new scientific breakthroughs.
Google announced on Wednesday an AI agent called ‘AI co-scientist’, which it said is “a multi-agent AI system built with Gemini 2.0 as a virtual scientific collaborator to help scientists generate novel hypotheses and research proposals, and to accelerate the clock speed of scientific and biomedical discoveries.”
AI agents are not just enhanced automation tools, but are developed so they can offer dynamic assistance to individuals and organisations with certain tasks.
AI co-scientist
Google noted that “in the pursuit of scientific advances, researchers combine ingenuity and creativity with insight and expertise grounded in literature to generate novel and viable research directions and to guide the exploration that follows.”
But it also noted that in many fields, this presents a conundrum, since it is challenging to navigate the rapid growth in the rate of scientific publications while integrating insights from unfamiliar domains.
“Motivated by unmet needs in the modern scientific discovery process and building on recent AI advances, including the ability to synthesise across complex subjects and to perform long-term planning and reasoning, we developed an AI co-scientist system,” said Google.
“The AI co-scientist is a multi-agent AI system that is intended to function as a collaborative tool for scientists,” it said. “Built on Gemini 2.0, AI co-scientist is designed to mirror the reasoning process underpinning the scientific method. …the AI co-scientist system is intended to uncover new, original knowledge and to formulate demonstrably novel research hypotheses and proposals, building upon prior evidence and tailored to specific research objectives.”
Google said the AI co-scientist is designed to generate novel research hypotheses, a detailed research overview, and experimental protocols. To do so, it uses a coalition of specialised agents – Generation, Reflection, Ranking, Evolution, Proximity and Meta-review – that are inspired by the scientific method itself.
These agents use automated feedback to iteratively generate, evaluate, and refine hypotheses, resulting in a self-improving cycle of increasingly high-quality and novel outputs, Google said.
Scientists can interact with the system in many ways, including by directly providing their own seed ideas for exploration or by providing feedback on generated outputs in natural language. The AI co-scientist also uses tools, like web-search and specialised AI models, to enhance the grounding and quality of generated hypotheses.
“AI co-scientist is a collaborative tool to help experts gather research and refine their work – it’s not meant to automate the scientific process,” said Google in another blog post. “We’re excited to see how researchers will use the system for their research.”
It should be remembered that Google’s AI unit, DeepMind, has made science a priority.
Indeed, DeepMind boss Demis Hassabis was a co-recipient of a Nobel Prize in Chemistry in October year for technology developed in the AI unit.
AI agents
But Google is not the only AI player currently offering AI agents.
In January 2025 OpenAI launched an AI agent (called ‘Operator’) that it said can emulate the work of a research analyst for areas including finance, science, policy and engineering, carrying out in “tens of minutes” what would take a human “many hours”.
Then earlier this month OpenAI launched an AI agent (called ‘Deep Research’) that it said can emulate the work of a research analyst for areas including finance, science, policy and engineering, carrying out in “tens of minutes” what would take a human “many hours”.
