Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Apr 30, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K

A multi-agent large language model framework for intelligent vendor evaluation and risk-aware procurement decisions.

Amey Joshi1, Mangal Singh2, Deepak Parashar3

  • 1Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University), Pune, India.

Scientific Reports
|April 28, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A curated dataset of 3,477 high-resolution Grapevine (Vitis vinifera) leaf images for automated detection of Black Rot, Esca, and Leaf Blight diseases.

Scientific data·2026
Same author

Massive retropharyngeal lipoma, a benign yet potentially lethal condition: a case report and review of the literature.

Journal of medical case reports·2026
Same author

Bioinformatics analysis of TRPV1 expression and its role in hepatocellular carcinoma prognosis.

Discover oncology·2026
Same author

Hybrid Aquila optimizer-Harris Hawks optimization for CNN hyperparameter tuning in brain tumor classification.

Scientific reports·2026
Same author

Correlation based feature importance analysis for improving machine learning stability predictions in hybrid PV systems.

Scientific reports·2026
Same author

Response to Letter to the Editor: Toward Precision Medicine in Portal Hypertension: Insights From the Carvedilol Versus Propranolol Meta-Analysis.

Journal of gastroenterology and hepatology·2026

This study introduces a Multi-Agent Large Language Model (LLM) framework for improved vendor evaluation. It analyzes structured and unstructured data for smarter procurement decisions and enhanced supply chain resilience.

Area of Science:

  • Supply Chain Management
  • Artificial Intelligence
  • Data Science

Background:

  • Traditional vendor selection methods are often suboptimal due to reliance on limited data points.
  • Evaluating vendor financial health, risk, market sentiment, and industry standards is complex.
  • Integrating diverse data sources for comprehensive vendor assessment remains a challenge.

Purpose of the Study:

  • To introduce a novel Multi-Agent Large Language Model (LLM) framework for advanced vendor evaluation.
  • To enhance procurement decision-making by analyzing both structured and unstructured data.
  • To improve supply chain resilience and long-term supplier relationship management.

Main Methods:

  • Development of a Multi-Agent LLM framework with specialized agents for financial analysis, risk profiling, sentiment monitoring, and industry benchmarking.
Keywords:
Industry benchmarkingLarge language models (LLMs)Multi-agent systemsRisk assessmentSentiment analysisVendor selection

More Related Videos

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

1.1K

Related Experiment Videos

Last Updated: Apr 30, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K
Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

1.1K
  • Integration of structured indicators (liquidity, profitability, solvency) and unstructured data (news, reviews, social media).
  • Utilizing agents to assess geopolitical, operational, and compliance risks, and benchmark against industry standards.

    • Main Results:

    • The framework provides data-driven, context-aware procurement recommendations by combining quantitative and qualitative insights.
    • Enables identification of appropriate vendors and real-time alerts for risk and performance deviations.
    • Facilitates vendor selection aligned with strategic objectives, risk reduction, and value enhancement.

    Conclusions:

    • The Multi-Agent LLM framework represents a significant advancement in smart procurement systems.
    • It offers a holistic approach to vendor evaluation, improving decision-making accuracy and efficiency.
    • The system contributes to building more resilient and value-oriented supply chains.