Metraipolis › archive › dc_54ab64becae6
LadderTeam: Dual-Agent Laddering Elicitation Framework — arXiv:2608.17029
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.17029
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:55:26.664Z
- SHA-256 of the archived text
17c2392504f874fce2384fbbeff1ca95227754d59cf85512d86224ad3ef028a9- Stable URL of this page
https://metraipolis.com/documento/dc_54ab64becae6
How to cite
LadderTeam: Dual-Agent Laddering Elicitation Framework — arXiv:2608.17029 — arXiv (en), https://arxiv.org/abs/2608.17029 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_54ab64becae6 (Metraipolis archive dc_54ab64becae6, sha256 17c2392504f874fce2384fbbeff1ca95227754d59cf85512d86224ad3ef028a9)
BibTeX
@misc{dc54ab64becae6,
title = {LadderTeam: Dual-Agent Laddering Elicitation Framework — arXiv:2608.17029},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.17029},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_54ab64becae6; sha256 17c2392504f874fce2384fbbeff1ca95227754d59cf85512d86224ad3ef028a9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17029. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Eliciting detailed and actionable software requirements from end-users is a critical phase in the iterative development of a software product or application. To ensure the feedback collected is detailed and actionable, software teams can leverage the laddering interview technique. While effective for ensuring granular and actionable items from the software feedback, these interviews are subject to several limitations. They are traditionally a manual process associated with a time and financial burden, limiting scalability; interviewers must balance probing for depth while managing interviewee behavioral and cultural constraints. To address these limitations, we present \textbf{LadderTeam}, an open, reproducible framework that automates UX wireframe interviews using a dual-agent Large Language Model (LLM) architecture. An active interviewer agent executes one of three probing strategies (ACV, 5-Whys, and JTBD) to elicit actionable software requirements from usability feedback comments, while a concurrent background Judge agent evaluates probe-response pairs and triggers real-time guardrails to prevent topic drift. To rigorously evaluate LLM laddering without participant variance confounds, we introduce a controlled simulation methodology utilizing scripted ground-truth transcripts to isolate probe quality as the sole experimental variable. Across 216 interviews, \textbf{LadderTeam} achieved 99.1\% chain convergence and an 81.0\% ground-truth actionable response match (86.1\% reluctant personality, 75.9\% terse personality) with zero drift across all runs. All evaluation code, all transcripts, inputs, and a live demonstration platform will be open-sourced upon acceptance.
Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-19 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2608.17029 — 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 2026-10-18T14:48:24.126Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).