自动化生成高质量论文，能整合文献与图表。
PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing
- 多智能体框架灵活处理非结构化研究材料
- 文献综述质量领先基线50%-68%，整体质量提升14%-38%
- 首个标准化基准支持可复现评估，适合科研人员快速成稿
将非结构化的研究素材转化为论文是人工智能驱动科学发现中的关键挑战，但尚未得到充分探索。现有自主写作系统与特定实验流程强绑定，且生成的文献综述流于表面。我们提出PaperOrchestra，一个用于自动化AI论文撰写的多智能体框架。该框架能灵活将无约束的写作前材料转化为可提交的LaTeX论文，包括全面的文献综合与自动生成的可视化内容，如图表和概念图。为评估性能，我们构建了PaperWritingBench，首个从200篇顶会论文逆向重构的原始材料基准，并配套一套完整的自动化评估工具。在与人类对比评估中，PaperOrchestra显著优于自主基线，在文献综述质量上胜出50%-68%，整体论文质量提升14%-38%。
原文摘要 · Abstract (English)
Synthesizing unstructured research materials into manuscripts is an essential yet under-explored challenge in AI-driven scientific discovery. Existing autonomous writers are rigidly coupled to specific experimental pipelines, and produce superficial literature reviews. We introduce PaperOrchestra, a multi-agent framework for automated AI research paper writing. It flexibly transforms unconstrained pre-writing materials into submission-ready LaTeX manuscripts, including comprehensive literature synthesis and generated visuals, such as plots and conceptual diagrams. To evaluate performance, we present PaperWritingBench, the first standardized benchmark of reverse-engineered raw materials from 200 top-tier AI conference papers, alongside a comprehensive suite of automated evaluators. In side-by-side human evaluations, PaperOrchestra significantly outperforms autonomous baselines, achieving an absolute win rate margin of 50%-68% in literature review quality, and 14%-38% in overall manuscript quality.
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。