arXiv cs.CL· Zhaoqian Xue, Shaoze Zhou, Xuexin Li, Junting Mu, Haozheng Liu, Zhongyin Wang, Yichun He, Renkai Ma, Hao Zhou, Sarah Bratt, Siyuan Ma, Chen Chen, Lingyao Li·· 2 天前AI 评分32
ReviewPilot：面向系统综述筛选与数据提取的多智能体系统
ReviewPilot: A Multi-Agent System for Screening and Data Extraction in Systematic Reviews
AI 导读
研究团队开发了对话式多智能体系统 ReviewPilot，将 PRISMA 流程从论文筛选自动化到信息提取，每条筛选决定附带理由、每个提取值标注来源。在流行病学专家综述上，ReviewPilot 在三种 LLM 上均优于单提示词 LLM 和 AgentSLR，筛选 macro F1 最高 0.776，提取 F1 最高 0.788。
正文 · 原文
Authors:Zhaoqian Xue, Shaoze Zhou, Xuexin Li, Junting Mu, Haozheng Liu, Zhongyin Wang, Yichun He, Renkai Ma, Hao Zhou, Sarah Bratt, Siyuan Ma, Chen Chen, Lingyao Li
Abstract:Systematic literature reviews follow the PRISMA process of screening scholarly works and extracting evidence from included studies. Deep research tools based on large language models (LLMs) can search and summarize the literature but do not record which studies are excluded or where extracted values come from. We develop a conversational multi-agent system called ReviewPilot that automates the PRISMA workflow from paper screening to information extraction. Researchers can tailor criteria and schemas through dialogue, and a project memory keeps their configurations and revisions. Each screening decision comes with its reason and each extracted value with its source. On epidemiological expert reviews, ReviewPilot outperforms a single-prompt LLM and AgentSLR across three LLMs, with screening macro F1 up to 0.776 and extraction F1 up to 0.788. Case studies in biomedicine and human-computer interaction show close agreement with human annotators, suggesting that ReviewPilot can transfer beyond epidemiology. Code is available at this https URL.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2610.21042 [cs.CL] |
| (or arXiv:2610.21042v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21042 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhaoqian Xue [view email]
[v1]
Thu, 15 Oct 2026 00:34:38 UTC (6,481 KB)
来源：arXiv cs.CL · arxiv.org