Heather Job

The automation of chemical research through self-driving laboratories (SDLs) promises to accelerate scientific discovery, yet the reliability and granular performance of the underlying AI agents remain critical, under-examined challenges. In this work, we introduce AutoLabs, a self-correcting, multi-agent architecture designed to autonomously translate natural-language instructions into executable protocols for a high-throughput liquid handler. The system engages users in dialogue, decomposes experimental goals into discrete tasks for specialized agents, performs tool-assisted stoichiometric calculations, and iteratively self-corrects its output before generating a hardware-ready file. We present a comprehensive evaluation framework featuring five benchmark experiments of increasing complexity, from simple sample preparation to multi-plate timed syntheses. Through a systematic ablation study of 20 agent configurations, we assess the impact of reasoning capacity, architectural design (single- vs. multi-agent), tool use, and self-correction mechanisms. Our results demonstrate that agent reasoning capacity is the most critical factor for success, reducing quantitative errors in chemical amounts (nRMSE) by over 85% in complex tasks. When combined with a multi-agent architecture and iterative self-correction, AutoLabs achieves near-expert procedural accuracy (F1-score > 0.89) on challenging multi-step syntheses. These findings establish a clear blueprint for developing robust and trustworthy AI partners for autonomous laboratories, highlighting the synergistic effects of modular design, advanced reasoning, and self-correction to ensure both performance and reliability in high-stakes scientific applications. Code: https://github.com/pnnl/autolabs

Traditional trial-and-error methods for materials discovery are too slow to meet the urgent demands posed by the rapid progression of climate change. This urgency has driven the increasing interest in integrating robotics and machine learning into materials research to accelerate experimental learning. However, idealized decision-making frameworks to achieve maximum sampling efficiency are not always compatible with high-throughput experimental workflows inside a laboratory. For multistep chemical processes, differences in hardware capacities can complicate the digital framework by introducing constraints on the maximum number of samples in each step of the experiment, hence causing varying batch sizes in variable selection within the same batch. Therefore, designing flexible sampling algorithms is necessary to accommodate the multi-step synthesis with practical sampling constraints unique to each high-throughput workflow. In this work, we designed and employed three strategies on a high-throughput robotic platform to optimize the sulfonation reaction of redox-active molecules used in flow batteries. Our strategies adapt to the multi-step experimental workflow, where their formulation and heating steps are separate, causing varying batch size requirements. By strategically sampling using clustering and mixed-variable batch Bayesian optimization, we were able to iteratively identify optimal conditions that maximize the yields. Our work presents a new approach that allows tailoring the ML decision-making to suit the practical constraints in individual HTP platforms, followed by performing resource-efficient yield optimization using already existing and available open-source Python libraries.

The solubility of redox-active organic molecules (ROMs) in non-aqueous redox flow batteries (NRFBs) is a critical factor determining the energy density of the system. However, the scarcity of comprehensive solubility data has hindered electrolyte development. In this study, we systematically investigate the solubility behavior of ROMs in the presence of supporting salts to propose practical electrolyte formulations for NRFBs. Using automated high-throughput experimentation, we screen the solubility of 2,1,3-benzothiadiazole (BTZ) and lithium bis(trifluoromethanesulfonyl)imide (LiTFSI) in various organic solvents. Leveraging a Random Forest inference model, we identify a binary solvent mixture of mxylene and acetonitrile, which dissolves 3 M of both BTZ and LiTFSI—exceeding the previously reported 2 M limit in pure acetonitrile. This enhanced solubility is achieved by the inclusion of a LiTFSI-phobic yet BTZ-philic solvent, which counterbalances the solubility competition between BTZ and LiTFSI, with the latter favoring highly polar solvents. This work introduces a promising electrolyte design strategy for NRFBs and highlights the effectiveness of high-throughput screening combined with advanced data analysis for optimizing complex multi-component systems. Furthermore, it emphasizes the urgent need for more comprehensive solubility data to facilitate the development of practical NRFB electrolytes.

Solubility is crucial for redox flow batteries as it affects their energy density. A data-driven approach based on AI/ML models can speed up the development of highly soluble redox active materials, but accurate solubility prediction remains elusive because of the lack of relevant databases. To overcome this deficiency, we developed a high-throughput experimentation process that combines a robotically controlled platform with high-throughput methodology to collect large-scale and high-quality solubility data. We demonstrate the potential utility and applicability of this high-throughput process by measuring the aqueous and non-aqueous solubilities of redox active materials and studying the effect of additives on their solubilities for both aqueous and non-aqueous redox flow battery applications. A redox flow battery based on our optimized negative electrolyte formulation and ferrocyanide positive electrolyte offers highly stable performance over 18 days (>100 cycles) with consistent capacity and a 24% boost in energy density.