ReqInOne: A Large Language Model-Based Agent for Software Requirements Specification Generation

TL;DR

ReqInOne is a modular LLM-based agent that systematically generates high-quality Software Requirements Specifications by mimicking human requirements engineering steps, outperforming prior holistic LLM approaches.

Contribution

It introduces a novel modular architecture for SRS generation using LLMs, improving accuracy, structure, and controllability over existing methods.

Findings

ReqInOne produces more accurate SRS than prior holistic LLM methods.

The modular design enhances output quality and consistency.

Requirement classification in ReqInOne matches or exceeds state-of-the-art models.

Abstract

Software Requirements Specification (SRS) is one of the most important documents in software projects, but writing it manually is time-consuming and often leads to ambiguity. Existing automated methods rely heavily on manual analysis, while recent Large Language Model (LLM)-based approaches suffer from hallucinations and limited controllability. In this paper, we propose ReqInOne, an LLM-based agent that follows the common steps taken by human requirements engineers when writing an SRS to convert natural language into a structured SRS. ReqInOne adopts a modular architecture by decomposing SRS generation into three tasks: summary, requirement extraction, and requirement classification, each supported by tailored prompt templates to improve the quality and consistency of LLM outputs. We evaluate ReqInOne using GPT-4o, LLaMA 3, and DeepSeek-R1, and compare the generated SRSs against those produced by the holistic GPT-4-based method from prior work as well as by entry-level requirements engineers. Expert evaluations show that ReqInOne produces more accurate and well-structured SRS documents. The performance advantage of ReqInOne benefits from its modular design, and experimental results further demonstrate that its requirement classification component achieves comparable or even better results than the state-of-the-art requirement classification model.