一句话：提出 DELTA，用 LLM 将用户故事自动分解为任务，并比较提示策略与模型，用专家评估验证质量评判。
将用户故事细化为任务对敏捷开发重要但繁琐。论文提出并评估 DELTA：一种基于 LLM 的方法，能从用户故事自动生成任务并评价分解质量。研究分两阶段：第一阶段比较不同提示策略、LLM 家族与规模，用文本相似度在人工和 LLM 生成分解上选择配置，但未找到一致最优配置；第二阶段用专家评估检验文本相似度差异是否反映专家判断，以及 DELTA 基于准则、由 LLM 评判的评估模块是否与专家一致。结果显示，DELTA 评估模块的排序比文本相似度更贴近专家判断；专家更偏好 LLM 评判前三的 LLM 生成分解，并愿意采用 DELTA。
Refining user stories (USs) into tasks is an important step in agile software development, as it translates software requirements into project management artifacts that are assigned to team members. This story-to-task decomposition can be tedious. In this paper, we propose and evaluate DELTA, a Large Language Model (LLM)-based approach that automatically generates tasks from USs and assesses the quality of the resulting decompositions. We conduct a two-phase empirical study to evaluate DELTA. In the first phase, we identify the best-performing DELTA configuration by comparing different prompting strategies, LLM families, and sizes using text similarity metrics on human-created and LLM-generated decompositions. The comparison based on these metrics did not identify a single consistently best-performing configuration. Therefore, in the second phase, we conducted an expert evaluation to determine whether the observed differences in text similarity are reflected in expert judgments and whether DELTA’s criteria-based evaluation module, which uses LLM judges, aligns with expert judgments. Our results show that DELTA’s evaluation module produces rankings that align more closely with expert judgments than text similarity metrics. Moreover, experts generally prefer the top three LLM-generated decompositions, as ranked by LLM judges, over those created by humans, and they express a willingness to adopt DELTA.
@inproceedings{paperbot12179,
title = {Can Large Language Models Decompose User Stories into Tasks? Exploring the Role of Prompting Strategies and Models},
author = {Delina Ly and Fatma Başak Aydemir and Fabiano Dalpiaz},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3837558}
}