Multi-Agent-Network-Based Idea Generator for Zinc-Ion Battery Electrolyte Discovery: A Case Study on Zinc Tetrafluoroborate Hydrate-Based Deep Eutectic Electrolytes.

Robson, Matthew J; Xu, Shengjun; Wang, Zilong; Chen, Qing; Ciucci, Francesco · Adv Mater · 2025

basic_science · Level V

Where this comes from

Abstract

Aqueous deep eutectic electrolytes (DEEs) offer great potential for low-cost zinc-ion batteries but often have limited performance. Discovering new electrolytes is therefore crucial, yet time-consuming and resource-intensive. In response, this work presents a Large Language Model (LLM)-based multi-agent network that proposes DEE compositions for zinc-ion batteries. By analyzing academic papers from the DEE field, the network identifies innovative, inexpensive, and sustainable Lewis bases to pair with Zn(BF<sub>4</sub>)<sub>2</sub>·xH<sub>2</sub>O. A Zn(BF<sub>4</sub>)<sub>2</sub>·xH<sub>2</sub>O-ethylene carbonate (EC) system demonstrates high conductivity (10.6 mS cm<sup>-1</sup>) and a wide electrochemical stability window (2.37 V). The optimized electrolyte enables stable zinc stripping/plating, achieves outstanding rate performance (81 mAh g<sup>-1</sup> at 5 A g<sup>-1</sup>), and supports 4000 cycles in Zn||polyaniline cells at 3 A g<sup>-1</sup>. Spectroscopic analyses and simulations reveal that EC coordinates to Zn<sup>2+</sup> <sub>,</sub> mitigating water-induced corrosion, while a fluorine-rich hybrid organic/inorganic solid electrolyte interphase enhances stability. This work showcases a pioneering LLM-driven approach to electrolyte development, establishing a new paradigm in materials research.