Prompt Engineering for Requirements Engineering: A Literature Review and Roadmap

2025-07-10

AI Summary

Large language models (LLMs) exhibit weak controllability and poor reproducibility in requirements engineering (RE), hindering their reliable adoption in practice. Method: Following the Kitchenham and Petersen secondary study protocol, we systematically reviewed and multidimensionally analyzed 35 empirical studies to develop PE4RE—a principled, task-oriented prompt engineering framework for RE. Contribution/Results: We propose the first “task–role” dual-dimensional taxonomy for RE-specific prompting, integrating techniques such as few-shot learning and chain-of-thought reasoning. Our analysis identifies alignment patterns between mainstream LLMs and prompt types, clarifies core application scenarios (e.g., requirements elicitation, validation, and traceability), and pinpoints persistent practical bottlenecks. Furthermore, we introduce a staged, reproducible, and usability-focused PE4RE roadmap—the first of its kind—thereby addressing critical gaps in controllability and reproducibility research for LLMs in RE.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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.

Problem

• Lack of clear guidance for effective LLM prompting in RE tasks
• Uncertainty and controllability issues in current LLM applications
• Fragmented landscape of PE techniques for RE needs organization

Innovation

• Hybrid taxonomy linking patterns to RE roles
• Systematic literature review on PE4RE
• Roadmap for evolving PE prototypes into workflows