BEIJING -- China's national supercomputing network on Tuesday unveiled its scientific-computing intelligent agent in Tianjin municipality.

According to the China Science Daily on Wednesday, the intelligent agent can automatically decompose research tasks, schedule compute resources, invoke simulation packages, analyze results, and generate reports by understanding natural-language instructions.

It compresses tasks that used to consume an entire day into roughly one hour and already supports nearly 100 high-frequency scientific-computing scenarios.

Supported by the available artificial intelligence community and repository, the intelligent agent can assemble more than 120 domain-specific knowledge bases spanning seven key scenarios, including AI, scientific intelligence, industrial simulation, and materials science, lowering the entry barrier for scientific computing and accelerating research productivity.

Scientific research is now transitioning from computational science to intelligent science, Qian Depei, an academician of the Chinese Academy of Sciences, was quoted as saying in the newspaper. Qian added that the emergence and evolution of scientific-computing agents integrate fragmented compute power, toolchains, and knowledge resources, offering researchers faster and more accessible innovation support.