Artifacts: An AI-Assisted Tool for Practically Relevant Research Problem Formulation in Software Engineering

[Background] Formulating well-defined and contextually grounded research problems is a critical step to ensure practical relevance in Software Engineering (SE). However, many research efforts remain disconnected from industry needs due to poorly structured problem formulations. Lean Research Inception (LRI) has been proposed as a collaborative framework to support the formulation and initial assessment of research problems by structuring key attributes and promoting alignment between researchers and practitioners. [Aims] This paper aims to support the formulation of practically relevant research problems by leveraging Artificial Intelligence (AI). [Method] We present an AI-assisted tool, called LRI Co-Assistant, that operationalizes the LRI framework in an interactive environment. LRI Co-Assistant integrates Large Language Models (LLMs) as a reasoning partner to assist in problem formulation. A realistic scenario is used to demonstrate the tool. [Results] The scenario shows that the LRI Co-Assistant can help transform an unstructured problem into a clearer, more consistent, and practice-aligned formulation, while reducing cognitive effort. [Conclusion] The initial results indicate that combining LRI with AI support can enhance early-stage research activities in SE. Future work includes empirical evaluation with researchers and practitioners.