Metraipolis › archive › dc_208d43e59fb4

DS-Lighting: Making Agent Harnesses Explicit for Data-Science Automation — arXiv:2608.28590

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28590
License (as archived)
CC0-1.0
Archived
2026-10-17T07:41:32.194Z
SHA-256 of the archived text
242353768511e16050b099f77a17c65cec79c4ec3c947b60222cc7c2e2fb6b24
Stable URL of this page
https://metraipolis.com/documento/dc_208d43e59fb4

How to cite

DS-Lighting: Making Agent Harnesses Explicit for Data-Science Automation — arXiv:2608.28590 — arXiv (en), https://arxiv.org/abs/2608.28590 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_208d43e59fb4 (Metraipolis archive dc_208d43e59fb4, sha256 242353768511e16050b099f77a17c65cec79c4ec3c947b60222cc7c2e2fb6b24)
BibTeX
@misc{dc208d43e59fb4,
  title = {DS-Lighting: Making Agent Harnesses Explicit for Data-Science Automation — arXiv:2608.28590},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28590},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_208d43e59fb4; sha256 242353768511e16050b099f77a17c65cec79c4ec3c947b60222cc7c2e2fb6b24},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28590. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Model (LLM) agents have shown promise for automating data-science workflows, yet their end-to-end performance depends critically on the agent harness that represents tasks, manages execution state, constrains output artifacts, and provides evaluation feedback. Existing data-science agents often leave this harness implicit, making results difficult to reproduce, compare, and attribute across heterogeneous tasks. We introduce DS-Lighting, a unified harness toolkit that makes harness design explicit for data-science automation. DS-Lighting decomposes the harness into four reusable layers: data, workflow, execution, and evaluation, and represents diverse agents as executable operator programs that support both predefined pipelines and adaptive search. We further integrate multiple open-source data-science benchmarks into an MLE-Bench-style task format, enabling controlled comparison under a shared task interface, sandboxed runtime, and metric protocol. Experiments across agents, harnesses, models, and ablations show that explicit harness design improves reproducibility, comparability, and reliability, while reducing avoidable system-level failures in end-to-end data-science workflows. Our code is available at this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.28590 — 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 2026-10-17T07:28:26.434Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).