Scientists in the United States have discovered an artificial intelligence (AI)-driven system that helps automate a powerful simulation method that predicts how atoms in materials interact.
The system, called atomistic simulations, can potentially accelerate discovery of materials for areas such as batteries, aerospace and electronics.
Explaining the method, research specialist at University of Illinois, Chicago, Uma Kornu said, “this multi-agent framework represents a fundamental shift in the discovery pipeline. We are moving away from the manual orchestration of fragmented tools toward an era of autonomous, collaborative AI.”
Researchers from the US Department of Energy’s (DOE) Argonne National Laboratory revealed that the AI-driven system could potentially reduce discovery time from months or years to just days.
“By automating these exhaustive investigations, we can potentially reduce the time requirements for discovering new materials from months or years to just days,” said Aditya Koneru, one of the study’s authors and an Argonne Scholar at the Argonne Leadership Computing Facility (ALCF).
According to them, this approach is particularly powerful because scientific discovery is inherently iterative. A failed experiment is not necessarily a dead end—it can provide information that changes the next hypothesis.
“Our system lowers the barrier to use atomistic simulations and enables them to be much more widely adopted across the scientific community,” said Subramanian Sankaranarayanan, one of the study’s lead authors. Sankaranarayanan is an Argonne materials scientist and a professor in the Department of Mechanical and Industrial Engineering at the University of Illinois Chicago.
The collaborative AI system efficiently performs complex simulations from start to finish. The framework is a team of collaborating agents: AI systems that perform tasks, interpret data and make decisions with limited human intervention.
The framework’s architecture was designed in collaboration with researchers at the Advanced Photon Source (APS), another DOE Office of Science user facility at Argonne, according to a press release.
“The multiagent AI framework streamlines the use of diverse tools to perform and analyze simulations,” said Katerina Vriza, a former CNM staff scientist at Argonne.
Using the framework is simple and straightforward. A human user enters a high-level prompt. The prompt can be a brief instruction like, “calculate the melting point of a gold-copper alloy.” In as little as a few minutes, the framework provides a detailed answer.
The framework’s execution of the simulation is much faster and results in fewer errors compared to what a human can do, as per the release.
A multi-agent workflow can divide a complicated research problem into smaller tasks. Agents can then communicate with one another, critique results and combine information from different sources.
