Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill

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.

Introduction. Turning a research idea into a complete academic paper requires substantially more than generating text. A researcher must identify relevant literature, design and run experiments, decide whether the resulting evidence supports the original hypothesis, revise claims when it does not, produce publication-ready figures, and maintain consistency across a manuscript that evolves over many stages. Recent autonomous research agents have begun to automate this broader process, demonstrating that language models can participate in ideation, experimentation, review, and paper generation [13, 28, 20, 7, 27]. However, these systems are typically implemented as standalone applications with their own orchestration layers and supporting infrastructure. This makes them powerful, but also separate from the coding environments in which much of the actual research work already takes place.