一句话：提出基于 LLM 的容器化 Web 工具 AISysRev，用于系统综述标题-摘要筛选，支持多模型与人工复核。
系统综述的标题-摘要筛选阶段工作量巨大。本文提出 AISysRev，一个基于大语言模型（LLM）的容器化 Web 筛选工具。它接受含标题与摘要的 CSV 文件，用户指定纳入/排除标准；支持多种 LLM（如 Gemini、Claude、Mistral、ChatGPT）及本地模型。工具实现零样本与少样本提示，并提供人工筛选界面，以 LLM 结果为参考。LLM 调用并行化，筛选速度约每分钟 100 至 300 篇。作者用 137 篇论文进行定性试用，将论文分为易纳入、易排除、边界纳入与边界排除四类；边界案例中 LLM 易出错，需人工干预。LLM 不能替代人类判断，但可减轻大量文献评估负担。
Conducting systematic reviews is laborious. In the screening or study selection phase, the number of papers can be overwhelming. Recent research has demonstrated that large language models (LLMs) can perform title-abstract screening and support humans in the task. To this end, we developed AISysRev, an LLM-based screening tool implemented as a containerized web application. The tool accepts CSV files containing paper titles and abstracts. Users specify inclusion and exclusion criteria. Multiple different LLMs can be used, such as Gemini, Claude, Mistral or ChatGPT via OpenRouter. We also support locally hosted models and any model compatible with the OpenAI SDK. AISysRev implements both zero-shot and few-shot prompting, and also allows for manual screening through interfaces that display LLM results as guidance for human reviewers. LLM calls are parallelized, meaning screening speed is typically between 100 to 300 papers per minute, depending on the model and the host. To demonstrate the tool's use in practice, we conducted a qualitative trial study with 137 papers using the tool. Our findings indicate that papers can be classified into four categories: Easy Includes, Easy Excludes, Boundary Includes, and Boundary Excludes. The Boundary cases, where LLMs are prone to errors, highlight the need for human intervention. While LLMs do not replace human judgment in systematic reviews, they can reduce the burden of assessing large volumes of scientific literature. Video: https://www.youtube.com/watch?v=HeblemlgnAQ Tool: https://github.com/EvoTestOps/AISysRev
DOI 原文 · arXiv · PDF（开放获取） · DBLP
@inproceedings{abs-2510-06708,
title = {AISysRev - LLM-based Tool for Title-abstract Screening},
author = {Aleksi Huotala and Miikka Kuutila and Olli-Pekka Turtio and Simo Sipilä and Mika Mäntylä},
booktitle = {FSE},
year = {2026},
doi = {10.1145/3803437.3806408}
}