Exécution de notre outil de synthèse sur un nouvel article

Résumé : The exponential growth of research articles has made it increasingly difficult for researchers to manually search and mine relevant problems. Traditional search mechanisms often fail to capture contextual nuances, leading to information overload. This paper proposes an automated framework that leverages large language models (LLMs), prompt engineering, and vector databases to efficiently mine and graph research problems. By integrating a retrieval-augmented generation (RAG) ecosystem with catered prompts and a retrieval chain, the system provides structured access to research problem statements in an open-access environment. Experimental implementation demonstrates the potential of this system to reduce researcher workload while improving precision in problem identification and knowledge representation.