Google AI aims to make best-in-class scientific software even better

"The company built evolutionary 'trees' of software tools for six tasks. The 'nodes' in each tree were single programs whose performance was assessed using a standard benchmark. The team created new nodes by prompting a large language model (LLM) to improve an existing one's performance. The researchers helped the LLM by feeding it summaries of research papers, specialist knowledge and other information. In each task, some of the resulting programs outperformed state-of-the-art tools."

""It's really cool to see big companies like Google using evolutionary approaches to make breakthroughs in other scientific fields," says Jenny Zhang, a computer scientist at the University of British Columbia in Vancouver, Canada, who has designed programs using similar methods. "It gives me hope that the research direction that I'm doing, when scaled up, can make a big impact." Google researchers answered questions from Nature about the work but declined to comment on the record because the manuscript has not yet been peer reviewed."

Google developed an AI-driven evolutionary workflow that builds evolutionary trees of software tools for six tasks. Each node was a single program evaluated with a standard benchmark. New nodes were created by prompting a large language model to improve existing programs, assisted with summaries of research papers, specialist knowledge and other information. Some resulting programs outperformed state-of-the-art tools for each task. The team answered questions from Nature but declined to comment on the record because the manuscript has not yet been peer reviewed. The system will be made available to scientists and many optimized tools are already online.

Read at Nature