AI辅助撰写综述论文，人机协作节省65.7%时间。
AISSISTANT: Human-AI Collaborative Review and Perspective Research Workflows in Data Science
- 设计双多智能体系统，支持全程人机协同生成科研综述。
- 使用增强文献检索的链式思考提示，提升生成质量。
- 适合需要高效撰写综述的科研人员，尤其关注数据科学领域。
高质量的科学综述与展望类论文需耗费大量时间和精力，限制了研究者对新兴知识的整合能力。尽管大型语言模型（LLMs）已用于构建自主科学工作流，但现有框架对人类干预的支持极为有限。我们提出 AIssistant，首个开源的、面向数据科学领域的人机协同生成科研综述与展望的工作流框架。AIssistant 采用由专用 LLM 驱动的智能体，并集成外部学术工具，支持人类在全流程中介入。框架包含两个核心多智能体系统：研究工作流（含7个智能体）和论文撰写工作流（含8个智能体）。我们通过人工专家评审和基于 LLM 的评估（遵循 NeurIPS 标准）进行了全面测试。实验表明，在使用增强文献搜索工具的链式思考提示下，OpenAI o1 达到最高质量评分。此外，人机交互调查显示，整体耗时减少65.7%。我们认为，本工作为数据科学领域的综述与展望类研究建立了人机协同的基准，证明代理增强的流程可显著降低工作量，同时通过战略性人类监督保障研究完整性。
原文摘要 · Abstract (English)
High-quality scientific review and perspective papers require substantial time and effort, limiting researchers' ability to synthesize emerging knowledge. While Large Language Models (LLMs) leverage AI Scientists for scientific workflows, existing frameworks focus primarily on autonomous workflows with very limited human intervention. We introduce AIssistant, the first open-source agentic framework for Human--AI collaborative generation of scientific perspectives and review research in data science. AIssistant employs specialized LLM-driven agents augmented with external scholarly tools and allows human intervention throughout the workflow. The framework consists of two main multi-agent systems: Research Workflow with seven agents and a Paper Writing Workflow with eight agents. We conducted a comprehensive evaluation with both human expert reviewers and LLM-based assessment following NeurIPS standards. Our experiments show that OpenAI o1 achieves the highest quality scores on chain-of-thought prompting with augmented Literature Search tools. We also conducted a Human--AI interaction survey with results showing a 65.7\% time savings. We believe that our work establishes a baseline for Human--AI collaborative scientific workflow for review and perspective research in data science, demonstrating that agent-augmented pipelines substantially reduce effort while maintaining research integrity through strategic human oversight.
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。