SerpApi.Org
Researchers at the US Department of Energy’s SLAC National Accelerator Laboratory are building a multi-agent AI system to find better ways to recover critical metals from lithium-ion battery waste.
The project will focus on metals including cobalt, nickel and manganese, which are valuable for battery manufacturing and other technologies. Recovering these materials from used batteries could help create a domestic supply while reducing dependence on imported critical minerals.
The SLAC-led team, working with the University of Southern California, plans to use multiple AI agents with specialized roles to explore how the metals can be separated from complex battery waste. The agents will draw on knowledge from fields including biochemistry and geology to propose recovery strategies, evaluate new approaches and learn from experimental results.
The project is part of the US Department of Energy’s Genesis Mission, a national initiative that aims to combine AI, supercomputing, quantum systems and advanced scientific instruments to accelerate research.
AI agents tackle battery waste
The researchers will run several cycles in which AI-generated strategies are tested through experiments. The project will run for nine months, with the team aiming to recover target metals at 80 percent purity or better.
“Over nine months, SLAC and the University of Southern California will run several AI-experiment cycles, aiming to recover target metals at 80 percent purity or better, while bench-marking this approach against conventional literature search and recovery methods,” Ahamed Irshad Maniyanganam, SLAC associate scientist and lead researcher on the project, said.
The researchers will compare the multi-agent approach with conventional methods based on literature searches and existing metal-recovery techniques. The goal is to determine whether AI-driven workflows can reduce the trial and error involved in finding effective ways to process battery waste.
A single spent electric vehicle battery can contain tens of pounds of valuable metals. However, recovering them can require large amounts of chemicals, produce substantial waste, and involve repeated testing to identify suitable extraction and separation processes.
The new approach is intended to help researchers explore a much wider range of potential chemical pathways. Instead of relying on one system to handle the entire research process, specialized AI agents will work on different parts of the problem and contribute to a shared experimental workflow.
Critical metals gain new route
The project could have implications beyond battery recycling. Cobalt, nickel, and manganese are considered important materials for modern energy technologies, and recovering them from used products could provide an additional source of these resources.
SLAC will also participate in 10 other Genesis Mission Phase I projects covering areas such as biotechnology, fusion energy, electronics and sensors, cosmology, particle physics and accelerator technology.
The broader Genesis Mission is designed to create an integrated scientific discovery platform that connects AI with large-scale computing and advanced research infrastructure. The Department of Energy says the first phase of funding is intended to identify promising research pathways and establish a foundation for future investment.
“SLAC’s role as a leading collaborator across a range of technologies positions us to advance AI’s transformative role in scientific discovery,” said SLAC Lab Director John Sarrao. “We appreciate the commitment of the Department of Energy in addressing these national challenges.”
For the battery recycling project, the immediate test will be whether a team of specialized AI agents can help scientists discover more efficient ways to recover valuable metals from waste while reaching the project’s 80 percent purity target.
