AIssistDM: A Plugin to Assist Non-specialist Decision-Makers in Search-Based Software Engineering Tools

Search-Based Software Engineering (SBSE) is a field that applies optimization algorithms to address complex problems in various software engineering domains. A significant challenge when using SBSE tools is the choice of parameter values related to the problem domain, which is usually performed by the Decision-Makers (DMs). This task is not trivial and critically influences the resulting solutions. Recognizing that DMs, mainly non-specialist ones, often struggle with these complexities, this paper introduces AIssistDM, a plugin developed to make adopting SBSE tools accessible without needing deep knowledge of their configuration parameters. The AIssistDM offers guided assistance by integrating Large Language Models (LLMs), particularly ChatGPT, to provide human-text generated suggestions of problem-domain parameters, improving decision-making. AIssistDM plugin was designed with a modular architecture to be integrated with different SBSE tools. The plugin has standard interfaces to enhance its capabilities without requiring extensive modifications in the integrated tools. A usage example describes integrating with the tool OPLA-Tool for Product Line Architecture (PLA) search-based design. This integration aids non-specialist DMs when configuring objective functions in OPLA-Tool. This study demonstrates how the AIssistDM integrates SBSE tools with ChatGPT by detailing the system architecture and core functionalities. The AIssistDM represents an advancement in the SBSE field, offering a new way to support the DM’s choice of parameters for SBSE tools. Video Available on https://doi.org/10.6084/m9.figshare.25942801.v1