ESCARGOT: an AI agent leveraging large language models, dynamic graph of thoughts, and biomedical knowledge graphs for enhanced reasoning
Bioinformatics · 04.02.2025 · 41 (2)
DOI: 10.1093/bioinformatics/btaf031 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 22.01.2025. Verfasst von Nicholas Matsumoto und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computational Biomedicine, Center for Artificial Intelligence Research and Education, Cedars Sinai Medical Center, West Hollywood, CA 9…. Hauptthemen laut MEDLINE: Software, Artificial Intelligence, Computational Biology. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NLM NIH HHS, NIA NIH HHS, Center for AI Research and Education at Cedars-Sinai Medical Center.
Abstract (Originalsprache)
Motivation LLMs like GPT-4, despite their advancements, often produce hallucinations and struggle with integrating external knowledge effectively. While Retrieval-Augmented Generation (RAG) attempts to address this by incorporating external information, it faces significant challenges such as context length limitations and imprecise vector similarity search. ESCARGOT aims to overcome these issues by combining LLMs with a dynamic Graph of Thoughts and biomedical knowledge graphs, improving output reliability, and reducing hallucinations. Result ESCARGOT significantly outperforms industry-standard RAG methods, particularly in open-ended questions that demand high precision. ESCARGOT also offers greater transparency in its reasoning process, allowing for the vetting of both code and knowledge requests, in contrast to the black-box nature of LLM-only or RAG-based approaches. Availability and implementation ESCARGOT is available as a pip package and on GitHub at: https://github.com/EpistasisLab/ESCARGOT.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Computational Biomedicine, Center for Artificial Intelligence Research and Education, Cedars Sinai Medical Center, West Hollywood, CA 90069, United States.
ORCID-Profile: Jason H Moore
Förderung
- NLM NIH HHS
- NIA NIH HHS
- Center for AI Research and Education at Cedars-Sinai Medical Center
- National Institutes of Health USA
Zitieren
APA
Matsumoto, N., Choi, H., Moran, J., Hernandez, M. E., Venkatesan, M., Li, X., Chang, J. H., Wang, P., & Moore, J. H. (2025). ESCARGOT: an AI agent leveraging large language models, dynamic graph of thoughts, and biomedical knowledge graphs for enhanced reasoning. Bioinformatics, 41(2). https://doi.org/10.1093/bioinformatics/btaf031
Vancouver
Matsumoto N, Choi H, Moran J, Hernandez ME, Venkatesan M, Li X, et al. ESCARGOT: an AI agent leveraging large language models, dynamic graph of thoughts, and biomedical knowledge graphs for enhanced reasoning. Bioinformatics. 2025;41(2). doi:10.1093/bioinformatics/btaf031
BibTeX
@article{Matsumoto2025,
author = {Matsumoto, Nicholas and Choi, Hyunjun and Moran, Jay and Hernandez, Miguel E and Venkatesan, Mythreye and Li, Xi and Chang, Jui-Hsuan and Wang, Paul and Moore, Jason H},
title = {ESCARGOT: an AI agent leveraging large language models, dynamic graph of thoughts, and biomedical knowledge graphs for enhanced reasoning},
journal = {Bioinformatics},
year = {2025},
volume = {41},
number = {2},
doi = {10.1093/bioinformatics/btaf031}
}
EUVIMED