{"ID":2893114,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.13937","arxiv_id":"2507.13937","title":"Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support","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.","short_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 universi...","url_abs":"https://arxiv.org/abs/2507.13937","url_pdf":"https://arxiv.org/pdf/2507.13937v2","authors":"[\"Jan Trienes\",\"Anastasiia Derzhanskaia\",\"Roland Schwarzkopf\",\"Markus Mühling\",\"Jörg Schlötterer\",\"Christin Seifert\"]","published":"2025-07-18T14:09:45Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"RAG\"]","has_code":false}