2026 · Conference paper

On the Viability of Requirements Generation from Code: An Experience Report

Studies a RAG-based, human-supervised pipeline for recovering requirements and code traces from two projects. It also tests deliberate generation of unimplemented requirements and requirements smells (potential quality issues), exposing verification and labeling difficulties.

Scope and limitations

The 188 generated requirements come from a student web application and Mattermost Desktop, using one model and PhD evaluators. Prompt choices, accumulated feedback and author-resolved labels affect validity. Findings concern this small experience study, not all code-to-requirements methods.

Why it fits this collection

Adds negative evidence and validation limits for recovering application specifications from code.

Publication and review details

Venue
IEEE REW 2026 / AIRE
Status
Conference paper
Publication / posting date
August 2026
Date source
IEEE-deposited Crossref proceedings month; first arXiv submission was June 24, 2026.
First arXiv submission
June 24, 2026
arXiv
2606.25550
Reviewed arXiv version
v1
DOI
10.1109/rew72749.2026.00023

Publication identity is verified through IEEE-deposited Crossref metadata and the official AIRE program; direct IEEE access returned an empty HTTP 202 response. Fulltext review uses arXiv v1. Figshare v4 declares CC BY 4.0 and its README describes data, prompts and an implementation. No archive or notebook was executed.

Sources reviewed

Source review only; experiments were not rerun for this collection. Cite the original authors using the linked paper or BibTeX.

Primary sources

  1. https://arxiv.org/abs/2606.25550
  2. https://arxiv.org/html/2606.25550v1
  3. https://api.crossref.org/works/10.1109/REW72749.2026.00023
  4. https://aire-ws.github.io/aire26/program.html
  5. https://alexkorn.de/papers/generation
  6. https://api.figshare.com/v2/articles/32393787
  7. https://ndownloader.figshare.com/files/64911339