Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Resource
  • Published:

SciToolAgent: a knowledge-graph-driven scientific agent for multitool integration

Nature Computational Science volume 5, pages 962–972 (2025)Cite this article

Subjects

Abstract

Scientific research increasingly relies on specialized computational tools, yet effectively utilizing these tools requires substantial domain expertise. While large language models show promise in tool automation, they struggle to seamlessly integrate and orchestrate multiple tools for complex scientific workflows. Here we present SciToolAgent, a large language model-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 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 nonexperts.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on SpringerLink
  • Instant access to the full article PDF.

USD 39.95

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Overview of SciToolAgent.
Fig. 2: Comparison results of different agents and foundation models.
Fig. 3: Workflow and results of protein design and analysis using SciToolAgent.
Fig. 4: Workflow and results of machine learning-based chemical reactivity prediction using SciToolAgent.
Fig. 5: Workflow and results of chemical synthesis and analysis using SciToolAgent.
Fig. 6: Workflow and results of MOF materials screening using SciToolAgent.

Similar content being viewed by others

Data availability

The toxic compound data were obtained from PubChem (https://pubchem.ncbi.nlm.nih.gov/#query=toxic&tab=compound), and the toxic protein data were sourced from UniProtKB (https://www.uniprot.org/uniprotkb?query=toxic&facets=reviewed%3Atrue). The SciToolEval dataset is available via Zenodo at https://doi.org/10.5281/zenodo.15691499 (ref. 44). Source data are provided with this paper.

Code availability

The source code of SciToolAgent is available via GitHub at https://github.com/hicai-zju/scitoolagent and via Zenodo at https://doi.org/10.5281/zenodo.15707181 (ref. 45).

References

  1. Birhane, A., Kasirzadeh, A., Leslie, D. & Wachter, S. Science in the age of large language models. Nat. Rev. Phys. 5, 277–280 (2023).

    Article  Google Scholar 

  2. Schick, T. et al. Toolformer: language models can teach themselves to use tools. Adv. Neural Inf. Process. Syst. 36, 68539–68551 (2023).

    Google Scholar 

  3. Yang, R. et al. GPT4Tools: teaching large language model to use tools via self-instruction. Adv. Neural Inf. Process. Syst. 36, 71995–72007 (2024).

    Google Scholar 

  4. Guo, T. et al. What can large language models do in chemistry? A comprehensive benchmark on eight tasks. Adv. Neural Inf. Process. Syst. 36, 59662–59688 (2023).

    Google Scholar 

  5. Zhao, W. X. et al. A survey of large language models. Preprint at https://arxiv.org/abs/2303.18223 (2023).

  6. Min, B. et al. Recent advances in natural language processing via large pre-trained language models: a survey. ACM Comput. Surveys 56, 1–40 (2023).

    Article  Google Scholar 

  7. Wang, L. et al. A survey on large language model based autonomous agents. Front. Comput. Sci. 18, 186345 (2024).

    Article  Google Scholar 

  8. Ramos, M. C., Collison, C. J. & White, A. D. A review of large language models and autonomous agents in chemistry. Chem. Sci. 16, 2514–2572 (2025).

    Article  Google Scholar 

  9. Boiko, D. A., MacKnight, R., Kline, B. & Gomes, G. Autonomous chemical research with large language models. Nature 624, 570–578 (2023).

    Article  Google Scholar 

  10. Janakarajan, N., Erdmann, T., Swaminathan, S., Laino, T. & Born, J. Language models in molecular discovery. In Drug Development Supported by Informatics (eds Satoh, H. et al.) 121–141 (Springer, 2024).

  11. Bran, A. M. et al. Augmenting large language models with chemistry tools. Nat. Mach. Intell. 6, 525–535 (2024).

    Article  Google Scholar 

  12. McNaughton, A. D. et al. CACTUS: chemistry agent connecting tool usage to science. ACS Omega 9, 46563–46573 (2024).

    Article  Google Scholar 

  13. Jin, Q., Yang, Y., Chen, Q. & Lu, Z. GeneGPT: augmenting large language models with domain tools for improved access to biomedical information. Bioinformatics 40, btae075 (2024).

    Article  Google Scholar 

  14. Huang, K. et al. CRISPR-GPT: an LLM agent for automated design of gene-editing experiments. Preprint at https://arxiv.org/abs/2404.18021 (2024).

  15. Liu, H. & Wang, H. GenoTEX: a benchmark for evaluating LLM-based exploration of gene expression data in alignment with bioinformaticians. Preprint at https://arxiv.org/abs/2406.15341 (2024).

  16. Ghafarollahi, A. & Buehler, M. J. ProtAgents: protein discovery via large language model multi-agent collaborations combining physics and machine learning. Digital Discovery 3, 1389–1409 (2024).

    Article  Google Scholar 

  17. Jia, S., Zhang, C. & Fung, V. LLMatDesign: autonomous materials discovery with large language models. Preprint at https://arxiv.org/abs/2406.13163 (2024).

  18. Kang, Y. & Kim, J. ChatMOF: an artificial intelligence system for predicting and generating metal–organic frameworks using large language models. Nat. Commun. 15, 4705 (2024).

    Article  Google Scholar 

  19. Wu, H. et al. ChatEDA: a large language model powered autonomous agent for EDA. IEEE Trans. Comput.-Aided Design Integr. Circuits Syst. 43, 3184–3197 (2024).

    Article  Google Scholar 

  20. Ni, B. & Buehler, M. J. MechAgents: large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge. Extreme Mech. Lett. 67, 102131 (2024).

    Article  Google Scholar 

  21. Yao, S. et al. ReAct: synergizing reasoning and acting in language models. In International Conference on Learning Representations https://iclr.cc/virtual/2023/oral/12647 (2023).

  22. He, J. et al. Control risk for potential misuse of artificial intelligence in science. Preprint at https://arxiv.org/abs/2312.06632 (2023).

  23. Liu, X. et al. ToolNet: connecting large language models with massive tools via tool graph. Preprint at https://arxiv.org/abs/2403.00839 (2024).

  24. Hao, S., Liu, T., Wang, Z. & Hu, Z. ToolkenGPT: augmenting frozen language models with massive tools via tool embeddings. Adv. Neural Inf. Process. Syst. 36, 45870–45894 (2024).

    Google Scholar 

  25. Shinn, N., Cassano, F., Gopinath, A., Narasimhan, K. & Yao, S. Reflexion: language agents with verbal reinforcement learning. Adv. Neural Inf. Process. Syst. 36, 8634–8652 (2024).

    Google Scholar 

  26. Ingraham, J. B. et al. Illuminating protein space with a programmable generative model. Nature 623, 1070–1078 (2023).

    Article  Google Scholar 

  27. Lin, Z. et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 1123–1130 (2023).

    Article  MathSciNet  Google Scholar 

  28. Atilgan, A. R. et al. Anisotropy of fluctuation dynamics of proteins with an elastic network model. Biophys. J. 80, 505–515 (2001).

    Article  Google Scholar 

  29. Bakan, A., Meireles, L. M. & Bahar, I. Prody: protein dynamics inferred from theory and experiments. Bioinformatics 27, 1575–1577 (2011).

    Article  Google Scholar 

  30. Cock, P. J. et al. Biopython: freely available Python tools for computational molecular biology and bioinformatics. Bioinformatics 25, 1422 (2009).

    Article  Google Scholar 

  31. Schwaller, P. et al. Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. ACS Central Science 5, 1572–1583 (2019).

    Article  Google Scholar 

  32. Pei, Q. et al. BioT5+: towards generalized biological understanding with IUPAC integration and multi-task tuning. In Findings of the Association for Computational Linguistics: ACL 2024, 1216–1240 (Association for Computational Linguistics, 2024).

  33. Papadatos, G. et al. SureChEMBL: a large-scale, chemically annotated patent document database. Nucleic Acids Res. 44, D1220–D1228 (2016).

    Article  Google Scholar 

  34. Kim, S. et al. Pubchem substance and compound databases. Nucleic Acids Res. 44, D1202–D1213 (2016).

    Article  Google Scholar 

  35. Bobbitt, N. S. et al. MOFX-DB: an online database of computational adsorption data for nanoporous materials. J. Chem. Eng. Data 68, 483–498 (2023).

    Article  Google Scholar 

  36. Nandy, A. et al. Mofsimplify, machine learning models with extracted stability data of three thousand metal–organic frameworks. Sci. Data 9, 74 (2022).

    Article  Google Scholar 

  37. Dubbeldam, D., Calero, S., Ellis, D. E. & Snurr, R. Q. RASPA: molecular simulation software for adsorption and diffusion in flexible nanoporous materials. Molecular Simulation 42, 81–101 (2016).

    Article  Google Scholar 

  38. BLAST: basic local alignment search tool. NIH https://blast.ncbi.nlm.nih.gov (2024).

  39. RDKit: open-source cheminformatics software. RDKit http://www.rdkit.org (2024).

  40. Bajusz, D., Rácz, A. & Héberger, K. Why is tanimoto index an appropriate choice for fingerprint-based similarity calculations? J. Cheminformatics 7, 1–13 (2015).

    Article  Google Scholar 

  41. Smith, T. F. et al. Identification of common molecular subsequences. J. Mol. Biol. 147, 195–197 (1981).

    Article  Google Scholar 

  42. Hu, E. J. et al. LoRA: low-rank adaptation of large language models. In International Conference on Learning Representations https://iclr.cc/virtual/2022/poster/6319 (2022).

  43. Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998–6008 (2017).

    Google Scholar 

  44. Yu, J. Dataset for the paper “SciToolAgent: A knowledge graph-driven scientific agent for multi-tool integration”. Zenodo https://doi.org/10.5281/zenodo.15691499 (2025).

  45. Yu, J. & Ding, K. HICAI-ZJU/SciToolAgent: V1.0.1. Zenodo https://doi.org/10.5281/zenodo.15707182 (2025).

Download references

Acknowledgements

This work is funded by National Science and Technology Major Project (2023ZD0120802, Q.Z.), Zhejiang Provincial ‘Jianbing’ ‘Lingyan’ Research and Development Program of China (2025C01097, K.D. and Q.Z.), NSFC62301480 (K.D.), NSFC62302433 (Q.Z.), NSFCU23A20496 (Q.Z.), NSFCU23B2055 (H.C.), the Fundamental Research Funds for the Central Universities (226-2023-00138, H.C.), Zhejiang Provincial Natural Science Foundation of China (LQ24F020007, Q.Z.) and Hangzhou West Lake Pearl Project Leading Innovative Youth Team Project (TD2023017, K.D.). The artificial-intelligence-driven experiments, simulations and model training were performed on the robotic AI-Scientist platform of the Chinese Academy of Sciences.

Author information

Author notes

  1. These authors contributed equally: Keyan Ding, Jing Yu.

Authors and Affiliations

  1. College of Computer Science and Technology, Zhejiang University, Hangzhou, China

    Keyan Ding & Huajun Chen

  2. Zhejiang Key Laboratory of Intelligent Manufacturing for Functional Chemicals, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou, China

    Keyan Ding, Jing Yu, Junjie Huang, Yuchen Yang, Qiang Zhang & Huajun Chen

  3. The Polytechnic Institute, Zhejiang University, Hangzhou, China

    Jing Yu

  4. ZJU-UIUC Institute, Zhejiang University, Haining, China

    Qiang Zhang

  5. State Key Laboratory of Ocean Sensing, Hangzhou, China

    Huajun Chen

Authors
  1. Keyan Ding
    View author publications

    Search author on:PubMed Google Scholar

  2. Jing Yu
    View author publications

    Search author on:PubMed Google Scholar

  3. Junjie Huang
    View author publications

    Search author on:PubMed Google Scholar

  4. Yuchen Yang
    View author publications

    Search author on:PubMed Google Scholar

  5. Qiang Zhang
    View author publications

    Search author on:PubMed Google Scholar

  6. Huajun Chen
    View author publications

    Search author on:PubMed Google Scholar

Contributions

K.D. conceived the study and designed the method. J.Y. and J.H. implemented the method and experiments. K.D. and J.Y. performed the result analyses. Y.Y. developed the online service. K.D., J.Y., Q.Z. and H.C. wrote and revised the paper. Q.Z. and H.C. supervised the entire project. All authors wrote the paper, reviewed it and approved the final paper.

Corresponding authors

Correspondence to Qiang Zhang or Huajun Chen.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Computational Science thanks Jihan Kim, Lei Shi and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Primary Handling Editor: Kaitlin McCardle, in collaboration with the Nature Computational Science team.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Supplementary Sections 1–5, Fig. 1 and Tables 1–3.

Reporting Summary

Source data

Source Data Fig. 2

Statistical source data.

Source Data Fig. 3

Statistical source data.

Source Data Fig. 4

Statistical source data.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ding, K., Yu, J., Huang, J. et al. SciToolAgent: a knowledge-graph-driven scientific agent for multitool integration. Nat Comput Sci 5, 962–972 (2025). https://doi.org/10.1038/s43588-025-00849-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Version of record:

  • Issue date:

  • DOI: https://doi.org/10.1038/s43588-025-00849-y

Search

Advanced search

Quick links

Nature Briefing AI and Robotics

Sign up for the Nature Briefing: AI and Robotics newsletter — what matters in AI and robotics research, free to your inbox weekly.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing: AI and Robotics