Agentic workflow enables the recovery of critical materials from complex feedstocks via selective precipitation

TL;DR

This paper introduces an AI-driven multi-agent workflow that enables rapid, selective recovery of critical materials from complex industrial feedstocks using automated instruments and simple chemicals, significantly speeding up traditional separation processes.

Contribution

The paper presents a novel multi-agentic AI workflow that accelerates critical materials recovery from complex feedstocks, reducing development time from months to days.

Findings

Achieved selective precipitation from real-world feedstocks

Reduced development timeline from months to days

Demonstrated adaptability and scalability of the process

Abstract

We present a multi-agentic workflow for critical materials recovery that deploys a series of AI agents and automated instruments to recover critical materials from produced water and magnet leachates. This approach achieves selective precipitation from real-world feedstocks using simple chemicals, accelerating the development of efficient, adaptable, and scalable separations to a timeline of days, rather than months and years.