ChemToolAgent: The Impact of Tools on Language Agents for Chemistry Problem Solving
This work addresses the gap in understanding tool benefits for chemistry agents, but it is incremental as it builds on existing agents like ChemCrow.
The paper tackled the problem of evaluating tool-augmented language agents for chemistry problem solving, finding that ChemToolAgent did not consistently outperform base LLMs without tools, with specialized tasks benefiting from tools but general questions relying more on reasoning ability.
To enhance large language models (LLMs) for chemistry problem solving, several LLM-based agents augmented with tools have been proposed, such as ChemCrow and Coscientist. However, their evaluations are narrow in scope, leaving a large gap in understanding the benefits of tools across diverse chemistry tasks. To bridge this gap, we develop ChemToolAgent, an enhanced chemistry agent over ChemCrow, and conduct a comprehensive evaluation of its performance on both specialized chemistry tasks and general chemistry questions. Surprisingly, ChemToolAgent does not consistently outperform its base LLMs without tools. Our error analysis with a chemistry expert suggests that: For specialized chemistry tasks, such as synthesis prediction, we should augment agents with specialized tools; however, for general chemistry questions like those in exams, agents' ability to reason correctly with chemistry knowledge matters more, and tool augmentation does not always help.