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

Journal: Bioinformatics (Oxford, England)
Published Date: Feb 4, 2025

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.

Authors

  • Nicholas Matsumoto
    Department of Computational Biomedicine, Center for Artificial Intelligence Research and Education, Cedars Sinai Medical Center, West Hollywood, CA 90069, United States.
  • Hyunjun Choi
    Department of Computational Biomedicine, Center for Artificial Intelligence Research and Education, Cedars Sinai Medical Center, West Hollywood, CA 90069, United States.
  • Jay Moran
    Yale School of Medicine, New Haven, CT, USA.
  • Miguel E Hernandez
    Department of Computational Biomedicine, Center for Artificial Intelligence Research and Education, Cedars Sinai Medical Center, West Hollywood, CA 90069, United States.
  • Mythreye Venkatesan
  • Xi Li
  • Jui-Hsuan Chang
    Department of Computational Biomedicine, Cedars Sinai Medical Center, Los Angeles, CA, USA.
  • Paul Wang
    Department of Computational Biomedicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
  • Jason H Moore
    University of Pennsylvania, Philadelphia, PA, USA.

Keywords

External Resources

Popular Topics
Recent Journals