An Empirical Study of Multi-Agent RAG for Real-World University Admissions Counseling

TL;DR

This paper introduces MARAUS, a multi-agent retrieval-augmented system for university admissions counseling in Vietnam, demonstrating high accuracy, low hallucination, and quick responses in real-world deployment with over 6,000 user interactions.

Contribution

It presents a novel multi-agent RAG system tailored for real-world university admissions, combining hybrid retrieval, multi-agent orchestration, and LLMs, with empirical validation in a low-resource setting.

Findings

92% accuracy in real-world queries

Hallucination rates reduced to 1.45%

Average response time below 4 seconds

Abstract

This paper presents MARAUS (Multi-Agent and Retrieval-Augmented University Admission System), a real-world deployment of a conversational AI platform for higher education admissions counseling in Vietnam. While large language models (LLMs) offer potential for automating advisory tasks, most existing solutions remain limited to prototypes or synthetic benchmarks. MARAUS addresses this gap by combining hybrid retrieval, multi-agent orchestration, and LLM-based generation into a system tailored for real-world university admissions. In collaboration with the University of Transport Technology (UTT) in Hanoi, we conducted a two-phase study involving technical development and real-world evaluation. MARAUS processed over 6,000 actual user interactions, spanning six categories of queries. Results show substantial improvements over LLM-only baselines: on average 92 percent accuracy, hallucination rates reduced from 15 precent to 1.45 percent, and average response times below 4 seconds. The system operated cost-effectively, with a two-week deployment cost of 11.58 USD using GPT-4o mini. This work provides actionable insights for the deployment of agentic RAG systems in low-resource educational settings.