Supporting software engineering tasks with agentic AI: Demonstration on document retrieval and test scenario generation

TL;DR

This paper presents agentic AI solutions for automating software engineering tasks like test scenario generation and document retrieval, demonstrating their effectiveness on real-world examples and exploring future research directions.

Contribution

Introduces novel agentic AI architectures for software engineering tasks, utilizing specialized agents and a star topology to improve automation and versatility.

Findings

Effective test scenario generation from detailed requirements

Versatile document retrieval including search and summarization

Demonstrated on real-world software engineering data

Abstract

The introduction of large language models ignited great retooling and rethinking of the software development models. The ensuing response of software engineering research yielded a massive body of tools and approaches. In this paper, we join the hassle by introducing agentic AI solutions for two tasks. First, we developed a solution for automatic test scenario generation from a detailed requirements description. This approach relies on specialized worker agents forming a star topology with the supervisor agent in the middle. We demonstrate its capabilities on a real-world example. Second, we developed an agentic AI solution for the document retrieval task in the context of software engineering documents. Our solution enables performing various use cases on a body of documents related to the development of a single software, including search, question answering, tracking changes, and large document summarization. In this case, each use case is handled by a dedicated LLM-based agent, which performs all subtasks related to the corresponding use case. We conclude by hinting at the future perspectives of our line of research.