<![CDATA[An artificial intelligence (AI)-based research proposal submission system is an innovative solution to improve efficiency and transparency in the academic selection process. This study develops a web-based system using the Laravel framework integrated with AI Agent to automatically review the title and abstract of lecturers' research proposals. This system is designed with a hybrid training approach, combining Supervised Learning (labeled data) and Reinforcement Learning from Human Feedback (RLHF), and utilizing Natural Language Processing (NLP) techniques for semantic analysis. The implementation results show that the system is able to evaluate research proposals with high accuracy, including checking title-abstract alignment, identifying problem backgrounds, and assessing originality. The system also provides real-time statistics and evaluation records, supporting more objective decision making. The contribution of the research lies in the use of AI to automate academic processes, reduce the workload of human reviewers, and improve the integrity of the research roadmap]]>
Copyrights © 2026
