发表机构
Siemens AG; Technical University of Munich（西门子股份公司; 慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出自优化多智能体框架Agent4RE，构建端到端RE基准数据集RE-E2E，其三种变体在8种LLM评估中均优于基线，增强变体评分最高，可作为工业端到端RE实用方案。
AI 中文摘要
现有基于大语言模型（LLM）的软件需求工程（RE）方法通常依赖基础提示策略或初步的智能体协作，未能充分发挥多智能体系统的全部潜力。同时，现有数据集聚焦于孤立的子任务，如需求提取、分类和完整性检测，缺乏从需求启发到生成的端到端RE基准。我们提出Agent4RE——一个自优化多智能体RE系统，它协调专门的智能体并包含两个迭代改进循环。为支持评估，我们构建了RE-E2E——一个基于人类编写的需求规格说明的真实世界数据集，可对RE工作流进行端到端评估。在此基础上，我们进一步提出两个增强版Agent4RE，分别融入自主自优化或结构化人类反馈，并分析它们在不同场景下的优势与局限。对8种大语言模型（LLM）的评估表明，所有三种Agent4RE变体在基于文本的指标上均比领域上下文增强的提示基线平均高出8%。两个增强变体获得最高的LLM作为评判者的评分和人类评分，在四分制上超过两个RE基线约0.8分。这种稳定的性能确立了Agent4RE作为工业环境中实用的端到端RE解决方案的地位。
英文摘要
Existing LLM-based approaches for software Requirements Engineering (RE) typically rely on basic prompting strategies or rudimentary agent collaboration, under-utilizing the full potential of multi-agent systems. Meanwhile, available datasets focus on isolated subtasks, such as requirements extraction, classification, and completeness detection, leaving the absence of an end-to-end RE benchmark that spans from requirements elicitation to generation. We present Agent4RE - a self-refining multi-agent RE system that orchestrates specialized agents and incorporates two iterative improvement loops. To support evaluation, we construct RE-E2E - a real-world dataset built from human-written requirement specifications, enabling end-to-end assessment of RE workflows. Building on this foundation, we further propose two enhanced Agent4RE versions that incorporate either autonomous self-refinement or structured human feedback, and analyze their strengths and limitations across different scenarios. Evaluation on 8 Large Language Models (LLMs) demonstrates that all three Agent4RE variants consistently outperform a domain-context-augmented prompting baseline by average 8% in text-based metrics. The two enhanced variants achieve the highest LLM-as-a-judge and human ratings, surpassing two RE baselines by approximately 0.8 points on a four-point scale. This consistent performance establishes Agent4RE as a practical end-to-end RE solution for industrial environments.
CommentsAccepted to the ASE@POVC track; The E2E requirements engineering benchmark is available https://zenodo.org/records/22815961
