Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Feb 4;41(2):btaf031.
doi: 10.1093/bioinformatics/btaf031.

ESCARGOT: an AI agent leveraging large language models, dynamic graph of thoughts, and biomedical knowledge graphs for enhanced reasoning

Nicholas Matsumoto  1 , Hyunjun Choi  1 , Jay Moran  1 , Miguel E Hernandez  1 , Mythreye Venkatesan  1 , Xi Li  1 , Jui-Hsuan Chang  1 , Paul Wang  1 , Jason H Moore  1
Affiliations

ESCARGOT: an AI agent leveraging large language models, dynamic graph of thoughts, and biomedical knowledge graphs for enhanced reasoning

Nicholas Matsumoto et al. Bioinformatics. .

Abstract

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.

PubMed Disclaimer

Figures

Figure 1.
Figure 1.
Algorithm flow chart (above) describing ESCARGOT’s approach to strategize, create python executable code, convert to machine readable XML code, deploy the Graph of Thoughts, and return the output.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Abujabal A, Roy RS, Yahya M et al. Never-ending learning for open-domain question answering over knowledge bases. In: Proceedings of the 2018 World Wide Web Conference (WWW'18), International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, CHE, pp. 1053–62, 2018.
    1. Besta M, Blach N, Kubicek A et al. Graph of Thoughts: Solving Elaborate Problems with Large Language Models. In: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, pp. 17682–90, Association for the Advancement of Artificial Intelligence (AAAI), 2024. 10.1609/aaai.v38i16.29720 - DOI
    1. Chen B, Zhang Z, Langrené N et al. Unleashing the potential of prompt engineering in large language models: a comprehensive review. arXiv, arXiv:2310.14735, 2023, preprint: not peer reviewed.
    1. Dilocker E, van Luijt B, Voorbach B et al. Weaviate. https://github.com/weaviate/weaviate
    1. Hong S, Zheng X, Chen J et al. Metagpt: meta programming for multi-agent collaborative framework. arXiv, arXiv:2308.00352, 2023, preprint: not peer reviewed.