Metraipolis › archive › dc_890597199843

A Retrieval-Augmented Automated Stakeholder for Requirements Elicitation Education: A Comparative Study — arXiv:2609.12576

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12576
License (as archived)
CC0-1.0
Archived
2026-10-16T03:34:02.983Z
SHA-256 of the archived text
36a46bbeee8875f0b2b2d6011936e7904e84c85ccc1fbfffbbcd58c040a2511e
Stable URL of this page
https://metraipolis.com/documento/dc_890597199843

How to cite

A Retrieval-Augmented Automated Stakeholder for Requirements Elicitation Education: A Comparative Study — arXiv:2609.12576 — arXiv (en), https://arxiv.org/abs/2609.12576 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_890597199843 (Metraipolis archive dc_890597199843, sha256 36a46bbeee8875f0b2b2d6011936e7904e84c85ccc1fbfffbbcd58c040a2511e)
BibTeX
@misc{dc890597199843,
  title = {A Retrieval-Augmented Automated Stakeholder for Requirements Elicitation Education: A Comparative Study — arXiv:2609.12576},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12576},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_890597199843; sha256 36a46bbeee8875f0b2b2d6011936e7904e84c85ccc1fbfffbbcd58c040a2511e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12576. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Developing the skills required for requirements engineering students to conduct effective requirements elicitation interviews is critical yet challenging, as it requires the development of soft skills in addition to technical knowledge. Role-playing is widely adopted in requirements engineering education to support the development of these skills but is often constrained by time and resource limitations. Although recent advances in large language models (LLMs) enable automated and interactive stakeholder simulations for role-playing, their application in requirements engineering education remains limited by hallucinations and inconsistent responses. To address these limitations, this study investigates the use of retrieval-augmented generation (RAG), implemented using the LangChain framework, to support requirements elicitation activities in a requirements engineering course. We conducted controlled experiments with 69 students, comparing cohorts who interacted with non-technical faculty role-players and those who engaged with RAG-based simulated stakeholders. The results indicate that while students perceived invited stakeholders as more realistic and engaging, the RAG-based automated stakeholder produced higher-quality elicitation questions and more complete feature identification.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-14 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.12576 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T03:11:31.869Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).