一句话：提出基于大语言模型的影响范围分析工具 AIST，自动解析需求、检索代码上下文并结合变更信息生成影响范围报告。
需求变更影响范围评估对软件质量至关重要，但面临两个难题：一是高度简化的「一句话需求」往往掩盖了复杂业务逻辑与大量系统依赖；二是提交中常交织着多个需求的代码改动，使人工评估既不完整又耗时，并易受认知偏差影响而遗漏关键影响点。本文提出 AIST（Analysis of the Impact Scope of the Task），一种基于大语言模型的自动化影响范围分析方法。它利用 LLM 的语义理解与规划能力，自动解析需求描述、从代码库中检索相关代码上下文，并整合代码变更信息，最终生成较完整的影响范围评估报告。作者在三个真实工业项目的 40 个历史需求变更上进行评估，取得 80.19% 的精确率、94.95% 的召回率与 86.35% 的 F1 值，显著提升了影响范围识别的完整性，并在检测交织代码变更方面表现出高敏感性。用户调研中新颖性得分为 6.32/7.00，总体满意度为 6.36/7.00，表明用户认为该工具有效提升了效率并降低了遗漏风险。
In modern software development, accurately assessing the impact scope of requirement changes is crucial for software quality, yet this task faces two major challenges. First, highly simplified requirement descriptions (one-sentence requirements) tend to conceal complex business logic and extensive system dependencies. Second, commits often intertwine code changes for multiple requirements, leading to impact assessments that are both incomplete and time-consuming. Traditional manual assessment methods are not only inefficient but also prone to cognitive biases, which often result in the omission of critical impact points. To address these problems, this paper proposes AIST (Analysis of the Impact Scope of the Task), an automated impact scope analysis approach based on Large Language Models (LLMs). AIST leverages the semantic understanding and planning capabilities of LLMs to automatically parse requirement descriptions, retrieve relevant code context from the codebase, and integrate code change information, thereby generating a comprehensive impact scope assessment report. We evaluated AIST on 40 historical requirement changes from three real-world industrial projects. The experimental results show that it achieves a precision of 80.19 %, a recall of 94.95 %, and an F1-score of 86.35 %, thereby significantly improving the completeness of impact scope identification and demonstrating high sensitivity in detecting tangled code changes. In a user survey, the novelty score was 6.32 out of 7.00, and the overall satisfaction score was 6.36 out of 7.00, indicating that users perceive that the tool effectively improves efficiency and reduces the risk of omissions.
@inproceedings{paperbot12295,
title = {Manifesting Implicit Dependencies in Requirements Task: An Automated Method Integrating Code Awareness and Change Analysis},
author = {Hui Ma and Jiajun Yang and Yan Chen and Pingjia Liao and Baoyu Zhao and Daoping Jiang},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834516}
}