Requirements engineering digest, week 36 of 2026

1. ReqEvolve: User-Oriented Software Self-Evolution through Automatic Requirement Interpretation

   Md Asif Iqbal Fahim, Alessio Ferrari

   arXiv (cs.SE), to appear at ASE 2026 · accepted

   Couples automatic requirements engineering with test-driven development so that a running system can turn high-level end-user requests into executable functionality at runtime, without a developer first translating them into technical specifications.

   Abstract

   The paradigm of software self-evolution enables systems to autonomously extend and reconfigure their own capabilities during execution in response to technical specifications. Yet requests for new functionality often originate from end users and are rarely expressed in technical terms. As a result, developers must translate user needs into technical specifications before the system can evolve, delaying early validation of the requested functionality by preventing users from immediately observing the resulting behaviour. To address this gap, we present ReqEvolve, a runtime code generation system that enables user-driven self-evolution by accepting high-level user requests. The system integrates automatic requirements engineering (RE) and test-driven development (TDD) to transform these requests into executable functionality through clarification, specification decomposition, test generation, and runtime integration. We evaluate ReqEvolve on 72 software evolution cases across 18 projects against two baselines: SpecFix, an RE-focused code generation approach, and an ablation variant of our system. ReqEvolve achieves 89.2% Pass@1, outperforming SpecFix by 18.8% (p < 0.01, r = 0.79, large effect) and the ablation baseline by 32.6% (p < 0.001, r = 0.88, large effect). These results provide initial evidence that user-driven self-evolution is a viable paradigm for autonomously extending software capabilities from user requests, thereby accelerating requirements validation prior to developer verification.

   Source: arxiv.org/abs/2609.10590

2. A retrieval-augmented automated stakeholder for requirements elicitation education: a comparative study

   Manal Binkhonain, Ohoud Mosa Alharbi

   Requirements Engineering Journal · published

   A controlled experiment with 69 students comparing human faculty role-players against a retrieval-augmented simulated stakeholder for elicitation interview training, finding the automated stakeholder produced better elicitation questions and more complete feature identification despite being perceived as less realistic.

   Abstract

   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.

   Source: doi.org/10.1007/s00766-026-00470-z · doi:10.1007/s00766-026-00470-z

3. Stakeholderbedarfe als neues RE-Artefakt für Querschnittsqualitäten

   Eduard C. Groen, Hannah Deters, Jakob Droste, Hartmut Schmitt

   Softwaretechnik-Trends 46(3) · published

   Proposes stakeholder needs as an RE artefact of its own, sitting upstream of system requirements, for cross-cutting qualities such as explainability and privacy that arise from personal characteristics rather than from any one system.

   Summary

   A two-page contribution arguing that expectations about cross-cutting qualities, explainability and privacy in particular, are poorly served by conventional system-specific user requirements, because they follow from personal characteristics and fundamental human needs and hold across whole categories of software. The authors introduce Stakeholderbedarfe, stakeholder needs, as a separate artefact type upstream of system requirements, and report two taxonomies, one for privacy needs and one for explainability needs, developed independently and then integrated. They close on what integrating the two made visible, and on formalising the artefact and extending it to accessibility, wellbeing and sustainability.

   Written for this digest, not by the authors. The source publishes no abstract of its own.

   Source: fb-swt.gi.de/fileadmin/FB/SWT/Softwaretechnik-Trends/Verzeichnis/Band_46_Heft_3/inf_stt_stakeholder_needs_2026.pdf