用交互式AI agents把系统综述时间从月缩短到小时
Completing A Systematic Review in Hours instead of Months with Interactive AI Agents
- 分语义区块+多智能体协作，精准处理文献
- 生成综述质量达人工水平的79.7%，提升27.2%
- 适合医疗从业者快速完成高质量综述
系统综述在医疗等高风险领域至关重要，但传统方法耗时数月且依赖大量人力。现有自动摘要方法因缺乏领域知识，难以准确识别相关研究。为此，我们提出InsightAgent——一种基于大语言模型的交互式人机协作AI代理。该系统通过语义划分文献库，并采用多智能体设计实现更聚焦的文献处理，显著提升综述生成质量。同时提供直观的文献与智能体轨迹可视化，使用户可实时监控并反馈。9名医学专业人士参与的用户研究表明，可视化与交互机制使综述质量提升27.2%，达到人工写作的79.7%；用户满意度提高34.4%。使用InsightAgent，临床医生仅需约1.5小时即可完成高质量系统综述，相比传统方法大幅提速。
原文摘要 · Abstract (English)
Systematic reviews (SRs) are vital for evidence-based practice in high stakes disciplines, such as healthcare, but are often impeded by intensive labors and lengthy processes that can take months to complete. Due to the high demand for domain expertise, existing automatic summarization methods fail to accurately identify relevant studies and generate high-quality summaries. To that end, we introduce InsightAgent, a human-centered interactive AI agent powered by large language models that revolutionize this workflow. InsightAgent partitions a large literature corpus based on semantics and employs a multi-agent design for more focused processing of literature, leading to significant improvement in the quality of generated SRs. InsightAgent also provides intuitive visualizations of the corpus and agent trajectories, allowing users to effortlessly monitor the actions of the agent and provide real-time feedback based on their expertise. Our user studies with 9 medical professionals demonstrate that the visualization and interaction mechanisms can effectively improve the quality of synthesized SRs by 27.2%, reaching 79.7% of human-written quality. At the same time, user satisfaction is improved by 34.4%. With InsightAgent, it only takes a clinician about 1.5 hours, rather than months, to complete a high-quality systematic review.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。