SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916867006791680 |
|---|---|
| author | Ding, Keyan Yu, Jing Huang, Junjie Yang, Yuchen Zhang, Qiang Chen, Huajun |
| author_facet | Ding, Keyan Yu, Jing Huang, Junjie Yang, Yuchen Zhang, Qiang Chen, Huajun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_20280 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration Ding, Keyan Yu, Jing Huang, Junjie Yang, Yuchen Zhang, Qiang Chen, Huajun Artificial Intelligence Computation and Language 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. |
| title | SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2507.20280 |