English

Enhancing Text Classification with a Novel Multi-Agent Collaboration Framework Leveraging BERT

Computation and Language 2025-02-27 v1 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.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}
}
R2 v1 2026-06-28T21:57:58.731Z