Metraipolis › archive › dc_7b14ebf29fdf

ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations — arXiv:2609.32868

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32868
License (as archived)
CC0-1.0
Archived
2026-10-07T21:00:43.096Z
SHA-256 of the archived text
4d3605b5c516eb8b0906349800ccc234cbb19e651d2125e29bf710c4714fc459
Stable URL of this page
https://metraipolis.com/documento/dc_7b14ebf29fdf

How to cite

ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations — arXiv:2609.32868 — arXiv (en), https://arxiv.org/abs/2609.32868 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7b14ebf29fdf (Metraipolis archive dc_7b14ebf29fdf, sha256 4d3605b5c516eb8b0906349800ccc234cbb19e651d2125e29bf710c4714fc459)
BibTeX
@misc{dc7b14ebf29fdf,
  title = {ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations — arXiv:2609.32868},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32868},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7b14ebf29fdf; sha256 4d3605b5c516eb8b0906349800ccc234cbb19e651d2125e29bf710c4714fc459},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32868. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Traditional scientific computing requires researchers to translate intent into environment configuration, resource requests, and executable jobs, then diagnose failures from scheduler and application logs. We present ASCEND (Autonomous Scientific Computing Engine and Novel Discovery), an AI-powered agent system, operated through a command-line or a local web chat interface, that runs the agent on the researcher's own laptop, reaching Slurm clusters and a GPU workstation over multiplexed authenticated SSH, with site-specific execution policies checked by locally executed tools. The language-model agent (Claude Code or Codex, chosen at each launch) is hosted remotely and holds no credentials; an account on each resource suffices, and a public installer links additional clusters or workstations. We report four recorded cases: (1) the agent closed a failure-recovery loop on a planted tensor-device fault, submitting, diagnosing, repairing, and resubmitting it; (2) it reproduced the published evaluation of a weather-forecasting model, recovering an incompletely stated evaluation protocol and agreeing with the published curves to 2.1% (z500) and 2.4% (t850), while identifying two discrepancies in the paper's released materials; (3) it parallelized a released 12,693-line geophysical solver under a requirement of bit-for-bit identity of exported outputs, reducing runtime from about twelve hours to about two; (4) that requirement exposed two instances of undefined behavior in the published solver, both repaired and reported upstream. These cases used ordinary scheduler commands; a separate, pre-specified evaluation of the optional policy validator rejected 29 of 30 constructed violations, held one for approval, and denied 3 of 14 legitimate requests. Autonomy was exercised under author supervision, and agent transcripts were not retained, so intervention rates are not independently verifiable.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Artificial Intelligence (cs.AI); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.32868 — 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 2026-10-07T20:29:02.484Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).