arXiv subjects

Kaicheng Huang

Publications and source records attributed to Kaicheng Huang.

3 recordsLinked to original sources

arXiv2025

Requirements-Driven Automated Software Testing: A Systematic Review

Automated software testing has significant potential to enhance efficiency and reliability within software development processes. However, its broader adoption faces considerable challenges, particularly concerning alignment between test generation methodologies and software requirements. REquirements-Driven Automated Software Testing (REDAST) addresses this gap by systematically leveraging requirements as the foundation for automated test artifact generation. This systematic literature review (SLR) critically examines the REDAST landscape, analyzing the current state of requirements input formats, transformation techniques, generated test artifacts, evaluation methods, and prevailing limitations. We conducted a thorough analysis of 156 relevant studies selected through a rigorous multi-stage filtering process from an initial collection of 27,333 papers sourced from six major research databases. Our findings highlight the predominance of functional requirements, model-based specifications, and natural language formats. Rule-based techniques are extensively utilized, while machine learning-based approaches remain relatively underexplored. Furthermore, most existing frameworks are sequential and dependent on singular intermediate representations, and while test cases, structured textual formats, and requirements coverage are common, full automation remains rare. We identify significant gaps related to automation completeness and dependency on input quality. This comprehensive synthesis provides a detailed overview of REDAST research and limitations, offering clear, evidence-based recommendations to guide future advancements in automated software testing.

cs.SE↗

arXiv2025

Multi-Modal Requirements Data-based Acceptance Criteria Generation using LLMs

Acceptance criteria (ACs) play a critical role in software development by clearly defining the conditions under which a software feature satisfies stakeholder expectations. However, manually creating accurate, comprehensive, and unambiguous acceptance criteria is challenging, particularly in user interface-intensive applications, due to the reliance on domain-specific knowledge and visual context that is not always captured by textual requirements alone. To address these challenges, we propose RAGcceptance M2RE, a novel approach that leverages Retrieval-Augmented Generation (RAG) to generate acceptance criteria from multi-modal requirements data, including both textual documentation and visual UI information. We systematically evaluated our approach in an industrial case study involving an education-focused software system used by approximately 100,000 users. The results indicate that integrating multi-modal information significantly enhances the relevance, correctness, and comprehensibility of the generated ACs. Moreover, practitioner evaluations confirm that our approach effectively reduces manual effort, captures nuanced stakeholder intent, and provides valuable criteria that domain experts may overlook, demonstrating practical utility and significant potential for industry adoption. This research underscores the potential of multi-modal RAG techniques in streamlining software validation processes and improving development efficiency. We also make our implementation and a dataset available.

cs.SE↗

arXiv2025

Prompt Engineering for Requirements Engineering: A Literature Review and Roadmap

Advancements in large language models (LLMs) have led to a surge of prompt engineering (PE) techniques that can enhance various requirements engineering (RE) tasks. However, current LLMs are often characterized by significant uncertainty and a lack of controllability. This absence of clear guidance on how to effectively prompt LLMs acts as a barrier to their trustworthy implementation in the RE field. We present the first roadmap-oriented systematic literature review of Prompt Engineering for RE (PE4RE). Following Kitchenham's and Petersen's secondary-study protocol, we searched six digital libraries, screened 867 records, and analyzed 35 primary studies. To bring order to a fragmented landscape, we propose a hybrid taxonomy that links technique-oriented patterns (e.g., few-shot, Chain-of-Thought) to task-oriented RE roles (elicitation, validation, traceability). Two research questions, with five sub-questions, map the tasks addressed, LLM families used, and prompt types adopted, and expose current limitations and research gaps. Finally, we outline a step-by-step roadmap showing how today's ad-hoc PE prototypes can evolve into reproducible, practitioner-friendly workflows.

cs.SE↗