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

2026-02-04

AI Summary

This work proposes a multi-agent system based on large language models to address the insufficient automation in test scenario generation and engineering documentation retrieval within software engineering. The system employs a star-topology architecture, wherein a central orchestrating agent coordinates multiple specialized task agents: one branch automatically generates test scenarios from requirement specifications, while the other supports document retrieval, question answering, change tracking, and summary generation. By leveraging an agent specialization mechanism, the system enhances both task-specific performance and overall scalability. Empirical evaluation on real-world software projects demonstrates the practical utility and effectiveness of the approach, particularly in terms of test generation accuracy and the diversity of documentation processing capabilities.

Technology Category

Multiagent Systems: TeamworkCognitive Modeling & Cognitive Systems: Agent ArchitecturesNatural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

Search and Retrieval-Augmented AI: Agentic searchSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• agentic AI
• software engineering
• test scenario generation
• document retrieval
• large language models

Innovation

• agentic AI
• test scenario generation
• document retrieval
• multi-agent architecture
• large language models