Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support

TL;DR

Marcel is an open-source, lightweight conversational agent designed to assist university prospective students by providing fast, personalized, and verifiable admission-related information, reducing staff workload.

Contribution

The paper introduces Marcel, a novel retrieval-augmented conversational system with an FAQ retriever that enhances answer accuracy and deployment simplicity in resource-limited academic environments.

Findings

Effective in real-world deployment for student support

Improves answer relevance with FAQ-based retrieval

Reduces staff workload significantly

Abstract

We present Marcel, a lightweight and open-source conversational agent designed to support prospective students with admission-related inquiries. The system aims to provide fast and personalized responses, while reducing workload of university staff. We employ retrieval-augmented generation to ground answers in university resources and to provide users with verifiable, contextually relevant information. We introduce a Frequently Asked Question (FAQ) retriever that maps user questions to knowledge-base entries, which allows administrators to steer retrieval, and improves over standard dense/hybrid retrieval strategies. The system is engineered for easy deployment in resource-constrained academic settings. We detail the system architecture, provide a technical evaluation of its components, and report insights from a real-world deployment.