Metraipolis › archive › dc_ca4ac4f90d00

AutoRecLab: Describe the Experiment, Get the Code! — arXiv:2609.21863

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21863
License (as archived)
CC0-1.0
Archived
2026-10-10T01:05:36.735Z
SHA-256 of the archived text
d5b27759cc829c8b1104963f4fe8adcd6240e95f8435fd96b4058ab7b51da1e7
Stable URL of this page
https://metraipolis.com/documento/dc_ca4ac4f90d00

How to cite

AutoRecLab: Describe the Experiment, Get the Code! — arXiv:2609.21863 — arXiv (en), https://arxiv.org/abs/2609.21863 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca4ac4f90d00 (Metraipolis archive dc_ca4ac4f90d00, sha256 d5b27759cc829c8b1104963f4fe8adcd6240e95f8435fd96b4058ab7b51da1e7)
BibTeX
@misc{dcca4ac4f90d00,
  title = {AutoRecLab: Describe the Experiment, Get the Code! — arXiv:2609.21863},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21863},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca4ac4f90d00; sha256 d5b27759cc829c8b1104963f4fe8adcd6240e95f8435fd96b4058ab7b51da1e7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21863. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Empirical evaluation is central to recommender-systems (RecSys) research, but turning experimental designs into executable code remains a manual and error-prone task. We present AutoRecLab, a Python-based autonomous RecSys lab that automates RecSys experiments from natural-language prompts. Given a research idea, AutoRecLab derives explicit experiment requirements, builds and validates a prototype, and iteratively expands it into the requested full experiment. The workflow combines retrieval-augmented generation (RAG) for documentation lookup, static type verification, and execution-steered tree search. In our demonstration, AutoRecLab autonomously implements an explicit-to-implicit feedback conversion study. In a baseline comparison across six algorithms and three datasets, 8 of 9 runs succeed at an average cost of approx- imately $1 per run with GPT-5.4-mini.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-21 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.21863 — 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 2026-10-10T00:23:42.479Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).