English

Using multi-agent architecture to mitigate the risk of LLM hallucinations

Artificial Intelligence 2025-07-03 v1

Abstract

Improving customer service quality and response time are critical factors for maintaining customer loyalty and increasing a company's market share. While adopting emerging technologies such as Large Language Models (LLMs) is becoming a necessity to achieve these goals, the risk of hallucination remains a major challenge. In this paper, we present a multi-agent system to handle customer requests sent via SMS. This system integrates LLM based agents with fuzzy logic to mitigate hallucination risks.

Keywords

Cite

@article{arxiv.2507.01446,
  title  = {Using multi-agent architecture to mitigate the risk of LLM hallucinations},
  author = {Abd Elrahman Amer and Magdi Amer},
  journal= {arXiv preprint arXiv:2507.01446},
  year   = {2025}
}
R2 v1 2026-07-01T03:42:48.052Z