ChemHAS: Hierarchical Agent Stacking for Enhancing Chemistry Tools
This work addresses the limitation of LLM-based agents in chemistry for researchers, though it appears incremental as it builds on existing agent-based approaches.
The paper tackles the problem of prediction errors in chemistry tools by proposing ChemHAS, a method that uses hierarchical agent stacking to enhance these tools, achieving state-of-the-art performance across four fundamental chemistry tasks.
Large Language Model (LLM)-based agents have demonstrated the ability to improve performance in chemistry-related tasks by selecting appropriate tools. However, their effectiveness remains limited by the inherent prediction errors of chemistry tools. In this paper, we take a step further by exploring how LLMbased agents can, in turn, be leveraged to reduce prediction errors of the tools. To this end, we propose ChemHAS (Chemical Hierarchical Agent Stacking), a simple yet effective method that enhances chemistry tools through optimizing agent-stacking structures from limited data. ChemHAS achieves state-of-the-art performance across four fundamental chemistry tasks, demonstrating that our method can effectively compensate for prediction errors of the tools. Furthermore, we identify and characterize four distinct agent-stacking behaviors, potentially improving interpretability and revealing new possibilities for AI agent applications in scientific research. Our code and dataset are publicly available at https: //anonymous.4open.science/r/ChemHAS-01E4/README.md.