Genesis Mission deploys AI agents to recover critical metals from lithium-ion battery waste

New computing system targets 80% purity in lithium battery metals

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. 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. 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.

SLAC to Lead Genesis Mission AI Project to Recover Critical Metals From Lithium-Ion Battery Waste

Researchers at SLAC and USC will use AI agents to develop pathways for separating out metals like cobalt, nickel and manganese, testing new approaches and learning from experiments. * SLAC will lead a Genesis Mission project focused on optimizing extraction of metals from spent lithium-ion batteries. * The project is part of a national Department of Energy effort to secure the U.S. supply of critical minerals. * The lab will partner in 10 additional projects announced today at the Genesis Mission Summit. Newswise -- The U.S. Department of Energy's SLAC National Accelerator Laboratory will lead a Genesis Mission project to help secure the nation's critical mineral supply by developing AI tools to improve recovery of valuable transition metals from spent lithium-ion batteries. The project, a collaboration between researchers at the SLAC-Stanford Battery Center and the University of Southern California, will address a key national science and technology challenge set out by the DOE earlier this year. In addition, SLAC will partner with other national labs, universities and industry leaders on 10 Genesis Mission projects announced today at the Genesis Mission Summit in Washington, D.C. The Genesis Mission is a historic national initiative led by the DOE, which is building the world's most powerful integrated science discovery platform. By uniting government, industry, academia, and philanthropy, it is accelerating breakthroughs in energy, scientific discovery, and national security through a new platform that combines AI, supercomputing, quantum systems, and advanced scientific instruments. The funding awards announced at the summit represent the first of two phases of awards from the Genesis Mission: Transforming Science and Energy with AI Request for Application (RFA). The goal of the Phase I RFA awards is to identify promising pathways toward transformative scientific capabilities and establish a foundation for future investment and scale. Project teams will design and demonstrate research workflows that integrate AI with scientific investigation, while rigorously evaluating whether those approaches can accelerate discovery, improve predictive capabilities, enhance experimentation, or generate new scientific insights. Building a team of AI agents to improve metal purity The SLAC-led project, "A Multi-agent AI Framework for Discovering Chemical Drivers of Selective Critical Metal Recovery from Complex Battery Waste," focuses on improving recovery of metals such as cobalt, nickel and manganese from lithium-ion batteries that have reached the end of their useful life. A single spent electric vehicle battery holds tens of pounds of such valuable metals, and recovering them could provide a domestic supply of materials, reducing today's imports. But extracting these metals currently requires large amounts of chemicals, generates significant waste, and involves extensive trial and error. The SLAC-led project will assemble multiple AI agents, each with a specialized role, to evaluate strategies across diverse fields, ranging from biochemistry to geology, to propose specific pathways for separating out the metals, testing new approaches and learning from experiments. "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. Coinvestigators on the project include Frank Abild-Pedersen, SLAC senior scientist and co-director of the SLAC-Stanford SUNCAT Center for Interface Science and Catalysis, Jagjit Nanda, distinguished scientist and executive director of the SLAC-Stanford Battery Center, and Jayakanth Ravichandran, professor at the USC Viterbi School of Engineering. In addition to the metals recovery project, SLAC will contribute to 10 additional Genesis Mission Phase I projects in areas including biotechnology, fusion energy, electronics and sensors, cosmology, particle physics, and accelerator technology. SLAC's premier facilities produce vast and uniquely varied scientific datasets that illuminate our world from the grand scale of the cosmos to the smallest scales of the motions of electrons. These data - along with the SLAC-Stanford ecosystem's expertise in algorithm development and its world-leading domain scientists - will fuel the AI revolution in science. The lab's contributions to the Genesis Mission bring together advanced computing infrastructure, AI innovation and data from world-leading scientific facilities to power the next generation of discovery. "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." ----------------------------------------------------------------------------------------------------------------------- About SLAC SLAC National Accelerator Laboratory explores how the universe works at the biggest, smallest and fastest scales and invents powerful tools used by researchers around the globe. As world leaders in ultrafast science and bold explorers of the physics of the universe, we forge new ground in understanding our origins and building a healthier and more sustainable future. Our discovery and innovation help develop new materials and chemical processes and open unprecedented views of the cosmos and life's most delicate machinery. Building on more than 60 years of visionary research, we help shape the future by advancing areas such as quantum technology, scientific computing and the development of next-generation accelerators. SLAC is operated by Stanford University for the U.S. Department of Energy's Office of Science. The Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time.