SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
This work addresses the problem of tool automation for scientific researchers, making advanced tools accessible to experts and non-experts, though it appears incremental as it builds on existing LLM and knowledge graph methods.
The paper tackles the challenge of automating complex scientific workflows by integrating multiple specialized tools, presenting SciToolAgent, an LLM-powered agent that uses a knowledge graph for tool selection and execution, and it significantly outperforms existing approaches in evaluations.
Scientific research increasingly relies on specialized computational tools, yet effectively utilizing these tools demands substantial domain expertise. While Large Language Models (LLMs) show promise in tool automation, they struggle to seamlessly integrate and orchestrate multiple tools for complex scientific workflows. Here, we present SciToolAgent, an LLM-powered agent that automates hundreds of scientific tools across biology, chemistry, and materials science. At its core, SciToolAgent leverages a scientific tool knowledge graph that enables intelligent tool selection and execution through graph-based retrieval-augmented generation. The agent also incorporates a comprehensive safety-checking module to ensure responsible and ethical tool usage. Extensive evaluations on a curated benchmark demonstrate that SciToolAgent significantly outperforms existing approaches. Case studies in protein engineering, chemical reactivity prediction, chemical synthesis, and metal-organic framework screening further demonstrate SciToolAgent's capability to automate complex scientific workflows, making advanced research tools accessible to both experts and non-experts.