Spark-to-Paper：以可組合技能實現端到端研究論文生成

摘要

將研究構想轉化為完整論文需要的不只是文字生成：系統必須檢索文獻、設計並執行實驗、根據證據修訂主張、產出可出版的圖形，並在漫長的生成過程中保持一致性。我們提出 Spark-to-Paper，這是一個端到端的研究論文生成系統，以現有程式碼助手內部的十三個可組合技能實現，無需獨立的代理平台或編排服務。Spark-to-Paper 將基於模型的判斷與可直接執行和驗證的確定性操作分離。它進一步將實驗規劃與報告分離，使所需證據在觀察結果之前即被指定，而稿件主張則根據實測結果進行修訂。為了提升長研究軌跡的可靠性，系統結合確定性完整性檢查與自我批判，並限制了我們稱為「自我反駁迴圈」的失敗模式——在該模式中，重複的實驗持續否決原始研究目標。Spark-to-Paper 也透過程式化繪圖為實驗結果產出可編輯的向量圖形，並以程式碼重建方式生成方法圖表。在八個受控研究主題中，Spark-to-Paper 達到 99.5% 的引用有效性和 96.4% 的圖形可編輯性。受控消融實驗將虛構偵測率從單次生成草稿的 14% 提升至完整完整性與審查堆疊的 92%，而對抗式審查達到 74% 的精確率。完整系統使用 1,190 萬個標記，每篇稿件花費 8.1 美元，平均需要 3.2 小時。這些結果表明，端到端的研究論文生成可以作為現有程式碼助手內部的輕量級、可組合工作流程來實現，同時保持實驗證據在主張被接受、修訂或放棄過程中的核心地位。

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.