Metraipolis › archive › dc_46286f4e2152

Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill — arXiv:2608.11924

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.11924
License (as archived): CC0-1.0
Archived: 2026-10-19T05:30:48.350Z
SHA-256 of the archived text: b5ac369ed1e348d1e2af238c37404a99cfda72c78e62c75e9f4e729874663ea7
Stable URL of this page: https://metraipolis.com/documento/dc_46286f4e2152

How to cite

Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill — arXiv:2608.11924 — arXiv (en), https://arxiv.org/abs/2608.11924 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46286f4e2152 (Metraipolis archive dc_46286f4e2152, sha256 b5ac369ed1e348d1e2af238c37404a99cfda72c78e62c75e9f4e729874663ea7)

BibTeX

@misc{dc46286f4e2152,
  title = {Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill — arXiv:2608.11924},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11924},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46286f4e2152; sha256 b5ac369ed1e348d1e2af238c37404a99cfda72c78e62c75e9f4e729874663ea7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11924. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.11924 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T05:15:39.226Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).