We introduce a novel multi-agent collaboration framework designed to enhance the accuracy and robustness of text classification models. Leveraging BERT as the primary classifier, our framework dynamically escalates low-confidence predictions to a specialized multi-agent system comprising Lexical, Contextual, Logic, Consensus, and Explainability agents. This collaborative approach allows for comprehensive analysis and consensus-driven decision-making, significantly improving classification performance across diverse text classification tasks. Empirical evaluations on benchmark datasets demonstrate that our framework achieves a 5.5% increase in accuracy compared to standard BERT-based classifiers, underscoring its effectiveness and academic novelty in advancing multi-agent systems within natural language processing.
View on arXiv@article{baban2025_2502.18653,
title={ Enhancing Text Classification with a Novel Multi-Agent Collaboration Framework Leveraging BERT },
author={ Hediyeh Baban and Sai A Pidapar and Aashutosh Nema and Sichen Lu },
journal={arXiv preprint arXiv:2502.18653},
year={ 2025 }
}