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

2025/07/02 by Abd Elrahman Amer, Amer, Abd Elrahman, Magdi Amer +1
Computer Science · #AI in Service Interactions #Architecture #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Fuzzy logic #Loyalty #Loyalty business model #Natural Language Processing Techniques #Quality (philosophy) #Service (business) #Service quality #Spam and Phishing Detection

paper · pdf · doi:10.48550/arxiv.2507.01446

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/07/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

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.

Citations

• Large Language Model based Multi-Agents: A Survey of Progress and Challenges
• Towards Mitigating Hallucination in Large Language Models via Self-Reflection
• The Rise and Potential of Large Language Model Based Agents: A Survey
• MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
• API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs
• GPTScore: Evaluate as You Desire
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Related

• Hallucination-aware Optimization for Large Language Model-empowered Communications
• OlaMind: Towards Human-Like and Hallucination-Safe Customer Service for Retrieval-Augmented Dialogue
• ProxyLLM : LLM-Driven Framework for Customer Support Through Text-Style Transfer
• LLM-Powered AI Agent Systems and Their Applications in Industry
• LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions