Spark-to-Paper：作为可组合技能的端到端研究论文生成

摘要

将研究想法转化为完整论文所需的不只是文本生成：系统必须检索文献、设计和执行实验、根据证据修改论断、生成达到发表标准的图表，并在整个长生成过程中保持一致性。我们提出Spark-to-Paper——一个端到端研究论文生成系统，在现有编码助手中以十三个可组合技能实现，无需单独的智能体平台或编排服务。Spark-to-Paper将基于模型的判断与可直接执行和校验的确定性操作相分离，并进一步将实验规划与报告环节分离，使得所需证据在观察结果之前即被明确规定，手稿论断则根据实测结果进行修订。为提高长研究轨迹的可靠性，系统将确定性完整性检查与自我批评相结合，并约束了一种我们称之为“自我反驳循环”的失败模式——在该模式中，重复实验持续否定原始研究目标。Spark-to-Paper还通过程序化绘图为实验结果生成可编辑矢量图，并通过基于代码的重建生成方法示意图。在八个受控研究主题上，Spark-to-Paper实现了99.5%的引用有效性和96.4%的图形可编辑性。受控消融研究将伪造检出率从单遍草稿的14%提升至完整完整性与评审栈下的92%，对抗性评审达到74%精确率。完整系统消耗1190万词元，每篇手稿成本8.1美元，平均耗时3.2小时。这些结果表明，端到端研究论文生成可以以轻量级、可组合的工作流形式在现有编码助手中实现，同时保持实验证据在论断被接受、修订或放弃过程中的核心地位。

English

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 evidence, produce publication-ready figures, and maintain consistency across a long generation process. We present Spark-to-Paper, an end-to-end research paper generation system implemented as thirteen composable skills inside an existing coding assistant, without requiring a separate agent platform or orchestration service. Spark-to-Paper separates model-based judgment from deterministic operations that can be directly executed and checked. It further separates experiment planning from reporting, so that required evidence is specified before results are observed and manuscript claims are revised according to measured outcomes. To improve reliability over long research trajectories, the system combines deterministic integrity checks with self-critique and bounds a failure mode we call the Self-Refutation Loop, in which repeated experiments continue to reject the original research objective. Spark-to-Paper also produces editable vector figures through programmatic plotting for experimental results and code-based reconstruction for generated method diagrams. Across eight controlled research topics, Spark-to-Paper achieves 99.5% citation validity and 96.4% figure editability. A controlled ablation increases fabrication detection from 14% for a single-pass draft to 92% with the full integrity and review stack, while adversarial review achieves 74% precision. The full system uses 11.9M tokens, costs $8.1 per manuscript, and requires 3.2 hours on average. These results show that end-to-end research paper generation can be implemented as a lightweight, composable workflow inside existing coding assistants while keeping experimental evidence central to how claims are accepted, revised, or abandoned.