Spark-to-Paper：作为可组合技能的研究论文端到端生成
原标题：Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill
AI 摘要
Hugging Face 每日论文介绍了 Spark-to-Paper，一个在现有编码助手中以十三个可组合技能实现的研究论文端到端生成系统。该系统将规划与报告分离，通过完整性检查减少捏造，并生成可编辑的矢量图。在八个受控研究主题上，它实现了 99.5% 的引用有效性和 96.4% 的图形可编辑性，完整系统平均每篇手稿成本 8.1 美元，耗时 3.2 小时。
正文节选
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill Abstract Spark-to-Paper is a lightweight, composable workflow inside coding assistants that generates research papers by separating planning from reporting, enforcing evidence-based claim revision, and using integrity checks to reduce fabrication. Turning a research idea into a complete paper requires more than text generation: the system must retrieve literature, design and execute experiments, revise claims according to