Automated evaluation of descriptive responses is a significant difficulty in educational technology, largely because of the significant limitations of conventional keyword-based grading systems. Automated tests are based on finding specific words or basic ideas they do not really check if the student truly understands the concept, what the words mean or the different ways a correct answer can be written. The automated evaluation methods have these limitations because they rely on matching phrases or fundamental principles. This can sometimes lead to grades that're not fair or consistent which is a big problem in online classes where reliability and consistency are really important, for automated evaluation methods. Automated evaluation methods need to be fair and consistent. Recent advances in Large Models of Language (LLMs) offer new possibilities for more intelligent evaluation based on logic and comprehension. Using explainable reasoning and semantic similarity, this work presents a multi-agent system for AI-driven assessment of descriptive responses. Preprocessing, evaluating semantic alignment, analyzing concept coverage, applying rubrics, producing explanations, and verifying the coherence between scores and feedback are just a few of the duties that the framework assigns to agents. The approach emphasizes conceptual comprehension rather than just keyword matching by fusing reasoning from LLMs with embedding-based semantic similarity. Additionally, a validation loop is employed to reduce variability and enhance grading reliability. The suggested approach is intended to enhance automated evaluation systems' scalability, transparency, and fairness. A comparison with baseline keyword-matching methods shows that the creation of structured feedback improves interpretability and alignment with human evaluators. This work provides a reliable and comprehensible solution for contemporary AI-driven educational assessment environments by combining multi-agent orchestration with semantic evaluation.
Automated Answer Evaluation; Semantic Similarity; Large Language Models; Multi-Agent Systems; Explainable AI; Educational Technology; Rubric-Based Scoring; Natural Language Processing.
International Journal of Trend in Scientific Research and Development - IJTSRD having
online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International
Journal which provides rapid publication of your research articles and aims to promote
the theory and practice along with knowledge sharing between researchers, developers,
engineers, students, and practitioners working in and around the world in many areas
like Sciences, Technology, Innovation, Engineering, Agriculture, Management and
many more and it is recommended by all Universities, review articles and short communications
in all subjects. IJTSRD running an International Journal who are proving quality
publication of peer reviewed and refereed international journals from diverse fields
that emphasizes new research, development and their applications. IJTSRD provides
an online access to exchange your research work, technical notes & surveying results
among professionals throughout the world in e-journals. IJTSRD is a fastest growing
and dynamic professional organization. The aim of this organization is to provide
access not only to world class research resources, but through its professionals
aim to bring in a significant transformation in the real of open access journals
and online publishing.