AI agents for science: accelerating research and discoveries

Views: 34

Specific AI agents for scientists represent advanced multi-agent digital systems designed to autonomously plan workflows, generate hypotheses, analyze complex genomics or chemical data and coordinate specialized tools like AlphaFold or ChEMBL. Other prominent systems include Google DeepMind’s Co-Scientist, Anthropic’s Claude Science and open frameworks like ToolUniverse. Thus, the AI agents can assist in “modelling human process of research” and accelerate discoveries/innovations in science. 

Background
In 2024, Demis Hassabis and John Jumper of Google DeepMind were awarded the Nobel Prose in chemistry for their neural network AlphaFold, which predicts the three-dimensional structures of proteins by learning from thousands of experimentally measured shapes. This devilish problem had resisted systematic attacks for half a century: e.g. AlphaFold seemed to have solved it once and for all; hence, the world became fixated on the promise of its approach.
Hassabis and his team called AlphaFold “the template for how AI can accelerate all of science to digital speed.” A wave of startups building foundation models for biology, chemistry and materials discovery raised billions of dollars, buoyed by DeepMind’s success. AlphaFold had shown that the combination of AI and sufficient data could make groundbreaking discoveries (even without specifically understand the underlying mechanisms involved) through the already available scientific achievements.
The primary condition for AlphaFold’s success was the existence of the Protein Data Bank, a data set of roughly 170,000 experimentally validated protein structures on which DeepMind’s team could train its model. The creation of the Protein Data Bank was not simple: it took 53 years of international scientific cooperation and, by a recent estimate, roughly $21 billion worth of experimental work to assemble. Efforts of that scale are infamously difficult to fund, next to impossible to coordinate, and hugely time-consuming to execute; they have often been unsuccessful as a result.
Source and citations from: https://www.technologyreview.com/2026/08/10/1141384/ai-agents-for-science/

The conditions that produced the likes of AlphaFold are rare, and the time it will take to meet those conditions in other fields would be measured in decades, not years. Instead, the acceleration of science will come about thanks to a specific digital – the AI agents.
However, AlphaFold is a specialized deep learning system rather than an autonomous AI agent, but its capabilities are increasingly integrated as foundational infrastructure within automated scientific and enterprise agent platforms. Developed by Google DeepMind and Isomorphic Labs, it a “predictive neural network” mapping molecular sequences to 3D.
Source: https://deepmind.google/science/alphafold/

AIs breakthroughs
Of course, there are a handful of fields where the mentioned “digital requirements” are met: weather forecasting, much of genomics, as well as some (although quite limited) areas of chemistry: these spheres may see AlphaFold-style breakthroughs soon, if they haven’t already. Government support for the production and coordination of those datasets will be critical, as the US Security Commission on Emerging Biotechnology has argued. But for presently most open questions in science is whether researchers need “a different plan” – at least in the short term, or there are some “quieter and more modest” ways to progress.
Scientists have always reasoned under uncertainty. Biologists working to identify new drug targets have never had perfect datasets. Instead, they combine docking calculations and known structures, factor in molecular dynamics, run a handful of binding assays, and use their judgment to weigh each method according to its particular strengths and points of failure. The skill of science is not in any single tool; it is synthesizing what many tools produce; and revising the results as the evidence comes in. This is how most working research actually proceeds. But until very recently, no software could do it.

AI agents presently can overcome these deficiencies: i.e. in a simple way, an AI agent represents a digital “reasoning engine” that has been given access to tools—digital or physical—and the capabilities to use them. Over the last few years, a fundamental architectural shift in AI has enabled the rapid proliferation of these programs, which are powered by large language models, dramatically reducing the need for scientifically specialized datasets. For science, this technological advancement represents a foundational change: it has allowed researchers to create digital tools that can mimic the iterative, highly contingent process of actual research. While tools like AlphaFold apply a powerful approach to a limited question, AI agents are inherently generalists. They do not represent a new way to do science—instead, they digitally model the human process of discovery.

The Google’s AI Co-Scientist model was announced in May 2026*): researchers gave it a one-page brief and a goal: figure out how antibiotic resistance spreads between bacterial species, a key driver of drug-resistant infections. The system spun up sub-agents: i.e. one drafted hypothesis from the literature, another picked them apart like a peer reviewer, a third ran tournaments to rank the strongest candidates, while a fourth refined the winning hypothesis. The AI agent concluded that resistance genes were hitching rides on bacterial viruses, borrowing whichever virus could ferry them into a new host. The hypothesis was correct: researchers at Imperial College London had spent a decade reaching the same conclusion through painstaking wet-lab work.
*) Note. Google’s AI Co-Scientist is a multi-agent artificial intelligence system built on the Gemini architecture and designed to act as a virtual research partner. It simulates the scientific method by reading massive amounts of literature, generating testable hypotheses, and running iterative debates and idea tournaments to refine research proposals.
Source: https://deepmind.google/blog/co-scientist-a-multi-agent-ai-partner-to-accelerate-research/

Google’s AI co-scientist’s example
Agents like “co-scientist” are still novel tools, and there are real challenges to overcome before they become a ubiquitous part of the scientific process: They are still liable to hallucinate, their judgment is not consistent and they have memory and input constraints that limit the time they can run autonomously. But these technical barriers will fall away, and consequently, scientists would begin to notice the compounding effects of these AI agents on the reliability, consistency and velocity with which science is done.
Perhaps most notably, AI agents offer a structural fix for science’s “reproducibility crisis,” the widespread problem of researchers’ inability to replicate each other’s results. For decades, the scientific community has begged researchers to share their raw data and exact code in an effort to standardize experimental processes. But researchers have long resisted this tedious administrative work, which happens after the interesting science is already done. Agents, in contrast, automatically log every move they make, creating an exact record of the method that led to their results and allowing for precise replication.
Another consequence would be in the amplification of scientific memory: the transfer of knowledge between researchers is a famously murky process; if it isn’t done over years of training and observation, graduate students are left to explore through the messy lab notebooks kept by decades of predecessors, looking for the details that will make or break their protocol. Thus, the AI agents would become an increasingly large part of the scientific process, though, a lab’s entire scientific history will be recorded in a central, standardized repository of institutional knowledge, the experts explain.

But the most important impact of AI agents will be speed. In any field, when testing an idea takes less time than arguing about it in a meeting, people stop debating and just run the test. An agent that can read a thousand papers in an hour, design 500 molecules, and learn from its failed tests by morning will bring down the cost of experimentation and fundamentally change the pace at which science gets done. It will also give researchers the freedom to chase bold, strange questions they never would have risked their time on before, opening scientific doors we have yet to imagine.
While the AlphaFold template will certainly be key to incredible discoveries, it alone will not bring us to the end of science. Instead, the shift toward agentic AI represents a much rarer tier of breakthrough: a tool that envelops every field of science at once. Historically, tools of such scope have arrived just a handful of times: calculus, statistical inference, spectroscopy, the computer, etc.; and each revealed a world of problems no one had thought to formulate. Such problems, in turn, defined their fields anew; hence with the AI agents, another such transformation is approaching…

    Bottom-line. Every great scientific breakthrough begins with a single, transformative idea. The spark of discovery relies on a researcher’s ability to connect disparate facts and formulate the right hypothesis to test. But in an era of information overload and increasingly complex challenges, the search for these needle-in-a-haystack ideas has become a significant bottleneck for progress. Scientific discovery is rarely a straight line; it is a cycle of “ideations” and hypothesis generation, critique and refinement. Scientists often reach their most profound insights only after wrestling with a complex problem for days, months and/or even years.
However, scientists still believe that AI agents can help dramatically accelerate the pace of breakthroughs by serving as a dedicated partner in the generation and refinement of all progressive and valuable scientific hypotheses.
References to: https://deepmind.google/blog/co-scientist-a-multi-agent-ai-partner-to-accelerate-research/