SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration

TL;DR

SciToolAgent is an LLM-powered scientific agent that uses a knowledge graph to automate and integrate multiple specialized scientific tools across various domains, enhancing workflow efficiency and accessibility.

Contribution

It introduces a knowledge graph-driven framework for multi-tool integration in scientific research, enabling intelligent tool selection and ethical automation.

Findings

Outperforms existing approaches on a curated benchmark.

Successfully automates complex workflows in biology, chemistry, and materials science.

Demonstrates practical utility in diverse scientific case studies.

Abstract

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.