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

Andrew Ritchhart, Sarah I. Allec, Pravalika Butreddy, Krista Kulesa, Qingpu Wang +3 more
3/16/2026
cond-mat.mtrl-scics.AI

No confident code implementation found for this paper.

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Decision-Focused Active Learning for Scale-Aware Critical-Materials Recovery

80% match2026

Toward Greater Autonomy in Materials Discovery Agents: Unifying Planning, Physics, and Scientists

73% match2025

Agentic schema-guided extraction of materials process knowledge from scientific literature

73% match2026

TritonDFT: Automating DFT with a Multi-Agent Framework

72% match2026

AIMS-EREA -- A framework for AI-accelerated Innovation of Materials for Sustainability -- for Environmental Remediation and Energy Applications

72% match2023

Rapid and Automated Alloy Design with Graph Neural Network-Powered LLM-Driven Multi-Agent Systems

72% match2024

Cite this paper

@article{ritchhart2026agentic,
  title  = {Agentic workflow enables the recovery of critical materials from complex feedstocks via selective precipitation},
  author = {Andrew Ritchhart and Sarah I. Allec and Pravalika Butreddy and Krista Kulesa and Qingpu Wang and Dan Thien Nguyen and Maxim Ziatdinov and Elias Nakouzi},
  year   = {2026},
  eprint = {2603.15491},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.15491v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2603.15491.svg)](https://codeofpaper.com/paper/2603.15491)

Discussion