一句话：提出 MLAssetSelection，一个自动提取并编目软件工程相关机器学习资产、支持榜单排名、需求式选择与实时更新的 Web 工具。
随着机器学习资产数量快速增长，软件工程师越来越难以从 Hugging Face 等大型注册库中识别出符合自身需求的模型与数据集；手工浏览过程耗时、易错，且很少针对软件工程（SE）任务进行定制。本文提出 MLAssetSelection，一个 Web 应用，能够自动抽取 SE 相关资产，并提供四项核心功能：（i）可配置的排行榜，支持跨多个基准与指标对模型进行排序；（ii）基于需求进行模型与数据集的选择；（iii）通过定时任务实现资产信息的实时自动更新；（iv）以用户为中心的功能，包括登录、个性化资产列表与可配置的告警通知。作者以演示视频的形式展示了该工具，摘要中未给出定量的实验评估或用户研究结果。
The rapid growth of machine learning assets has made it increasingly difficult for software engineers to identify models and datasets that match their specific needs. Browsing large registries, such as Hugging Face, is time-consuming, error-prone, and rarely tailored to Software Engineering (SE) tasks. We present MLAssetSelection, a web application that automatically extracts SE assets and supports four key functionalities: (i) a configurable leaderboard for ranking models across multiple benchmarks and metrics; (ii) requirements-based selection of models and datasets; (iii) real-time automated updates through scheduled jobs that keep asset information current; and (iv) user-centric features including login, personalized asset lists, and configurable alert notifications. A demonstration video is available at https://youtu.be/t6CJ6P9asV4.
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2601-13460,
title = {A Tool for Automatically Cataloguing and Selecting Pre-Trained Models and Datasets for Software Engineering},
author = {Alexandra González and Oscar Cerezo and Xavier Franch and Silverio Martínez-Fernández},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3806403}
}