一句话：提出 LLM 能否替代依赖标注、特征工程与重训练的经典 ML 流水线这一核心问题。
本文关注大语言模型在软件工程任务中的广泛应用，并提出一个基础且新颖的问题：LLM 在多大程度上能够取代依赖标注数据、特征工程和重训练的经典机器学习流水线？标题暗示其思路可能是将传统 ML 流水线重新解释为基于 LLM 的推理过程，但给出的摘要尚未说明具体任务、方法、实验设置或结果，因此目前只能确认其研究动机与核心问题，无法概括关键实证结论。
Large Language Models (LLMs) are increasingly used in software engineering tasks due to their strong performance across diverse applications. In this paper, we ask a fundamental and novel question: To what extent can LLMs replace traditional machine learning pipelines that rely on labeled data, feature engineering, and retraining?
@inproceedings{paperbot11989,
title = {Replacing Training with Reasoning: Reinterpreting Classic ML Pipelines with LLMs},
author = {Marco Alecci and Jordan Samhi and Tegawendé F. Bissyandé and Jacques Klein},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3786582.3786807}
}