用知识图谱让AI自动调用数百个科研工具，搞定复杂研究流程。
SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
- 基于科学工具知识图谱，智能选择并调度多个科研工具。
- 在蛋白质工程等任务中，自动化成功率显著高于现有方法。
- 适合科研人员和非专家快速使用高端计算工具。
科学研究日益依赖专用计算工具，但高效使用这些工具需要大量领域知识。尽管大语言模型（LLMs）在工具自动化方面展现出潜力，但在协调多个工具完成复杂科研工作流时仍存在困难。本文提出SciToolAgent，一个基于LLM的智能代理，可自动化跨生物、化学和材料科学领域的数百个科研工具。其核心是一个科学工具知识图谱，通过图检索增强生成实现智能工具选择与执行。该代理还集成了全面的安全检查模块，确保工具使用的负责任与伦理性。在精心构建的基准测试中，SciToolAgent显著优于现有方法。在蛋白质工程、化学反应性预测、化学合成及金属有机框架筛选等案例研究中，进一步验证了其自动化复杂科研工作流的能力，使高级研究工具对专家与非专家均更易获取。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。