用多智能体检索增强系统帮越南大学招生，真实场景下准确率92%。
An Empirical Study of Multi-Agent RAG for Real-World University Admissions Counseling
- 分角色智能体协作+检索增强，提升回答准确性
- 真实用户交互超6000次，幻觉率从15%降至1.45%
- 低成本部署，两周仅花11.58美元，适合资源有限学校
本文介绍MARAUS（多智能体与检索增强的大学招生系统），一个在越南实际部署的高等教育招生咨询对话式AI平台。尽管大语言模型（LLMs）具备自动化咨询任务的潜力，但多数现有方案仍停留在原型或合成基准测试阶段。MARAUS通过结合混合检索、多智能体编排和基于LLM的生成，打造适用于真实大学招生场景的系统。在与河内交通科技大学（UTT）合作下，我们开展了两阶段研究：技术开发与真实世界评估。MARAUS处理了超过6,000次实际用户交互，涵盖六类查询。结果表明，相比纯LLM基线，系统平均准确率达92%，幻觉率从15%降至1.45%，平均响应时间低于4秒。系统运行成本可控，使用GPT-4o mini进行为期两周的部署成本为11.58美元。本研究为低资源教育环境中代理型RAG系统的落地提供了可操作的洞见。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。