Metraipolis › archive › dc_9535d24ff68e

How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering? — arXiv:2609.40303

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.40303
License (as archived)
CC0-1.0
Archived
2026-10-07T12:43:09.717Z
SHA-256 of the archived text
0ba886cad2afe4a3925eeb63973a41e0c0ffd258fbd6dd30c4dfa67ccdf02f5d
Stable URL of this page
https://metraipolis.com/documento/dc_9535d24ff68e

How to cite

How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering? — arXiv:2609.40303 — arXiv (en), https://arxiv.org/abs/2609.40303 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9535d24ff68e (Metraipolis archive dc_9535d24ff68e, sha256 0ba886cad2afe4a3925eeb63973a41e0c0ffd258fbd6dd30c4dfa67ccdf02f5d)
BibTeX
@misc{dc9535d24ff68e,
  title = {How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering? — arXiv:2609.40303},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.40303},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9535d24ff68e; sha256 0ba886cad2afe4a3925eeb63973a41e0c0ffd258fbd6dd30c4dfa67ccdf02f5d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40303. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnation over long-horizon cycles and limited Large Language Model (LLM) primitives, modern MLE agents are deployed on top of increasingly elaborate machinery: multi-agent orchestrators, dedicated retrieval subagents, and more. While such harnesses expand, the use of more primitive but improved coding agents - where LLMs have direct access to the execution environment through read, write, and bash primitives - has received little attention in the field. In this paper we find that, under an equal time budget and the same frontier LLM backbone, open-source state-of-the-art harnesses provide no advantages over a single session of a minimal-harness coding agent baseline, pointing to the backbone as the primary driver for performance. Via a series of large-scale systematic ablation studies, we argue that the machinery layers become redundant in the coding agent setting. We conclude that the effort spent elaborating hand-crafted harnesses around strong models yields poor returns for current MLE benchmarks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.40303 — 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 2026-10-07T12:14:13.817Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).