Towards LLM-Enhanced Product Line Scoping

2025-07-31

AI Summary

Traditional product line scoping relies heavily on formal feature models and manual analysis, resulting in low efficiency and difficulty balancing commercial value with technical feasibility. This paper proposes a large language model (LLM)-based, natural-language–driven interactive scoping method that enables users to generate, evaluate, and trade off feature model variants directly from informal requirement descriptions. Empirically validated in the smart home domain, the approach demonstrates LLMs’ effectiveness in interpreting domain semantics, detecting constraint conflicts, and quantifying commercial–technical trade-offs. The study breaks the strong dependence of conventional methods on formal modeling expertise and domain specialists, and—critically—constitutes the first systematic investigation into the applicability boundaries and integration challenges of LLMs within core product line engineering activities. It thereby establishes both theoretical foundations and practical pathways for developing intelligent, interpretable, and automated scoping tools.

Technology Category

• Natural Language Processing: (Large) Language Models
• 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
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The idea of product line scoping is to identify the set of features and configurations that a product line should include, i.e., offer for configuration purposes. In this context, a major scoping task is to find a balance between commercial relevance and technical feasibility. Traditional product line scoping approaches rely on formal feature models and require a manual analysis which can be quite time-consuming. In this paper, we sketch how Large Language Models (LLMs) can be applied to support product line scoping tasks with a natural language interaction based scoping process. Using a working example from the smarthome domain, we sketch how LLMs can be applied to evaluate different feature model alternatives. We discuss open research challenges regarding the integration of LLMs with product line scoping.

Problem

• Balancing commercial relevance and technical feasibility in product line scoping
• Reducing time-consuming manual analysis in traditional scoping approaches
• Integrating LLMs for natural language-based scoping process support

Innovation

• LLMs enhance product line scoping
• Natural language interaction replaces manual analysis
• LLMs evaluate feature model alternatives