Metraipolis › archive › dc_6df67051d4ef

Auto-RecSys: Harnessing Autonomous Research Agents for Industry-Scale Recommender System — arXiv:2609.10922

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.10922
License (as archived)
CC0-1.0
Archived
2026-10-16T05:40:40.469Z
SHA-256 of the archived text
ace339da13392ff7467f6e6a4a12d20e0085977524f46e4ac0656bed41284fe8
Stable URL of this page
https://metraipolis.com/documento/dc_6df67051d4ef

How to cite

Auto-RecSys: Harnessing Autonomous Research Agents for Industry-Scale Recommender System — arXiv:2609.10922 — arXiv (en), https://arxiv.org/abs/2609.10922 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6df67051d4ef (Metraipolis archive dc_6df67051d4ef, sha256 ace339da13392ff7467f6e6a4a12d20e0085977524f46e4ac0656bed41284fe8)
BibTeX
@misc{dc6df67051d4ef,
  title = {Auto-RecSys: Harnessing Autonomous Research Agents for Industry-Scale Recommender System — arXiv:2609.10922},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10922},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6df67051d4ef; sha256 ace339da13392ff7467f6e6a4a12d20e0085977524f46e4ac0656bed41284fe8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10922. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Auto-research agents have shown the potential to automate hypothesis generation, experiment execution, and iterative refinement. However, scaling this paradigm to industry-scale recommendation models introduces two challenges: (1) long feedback loops, where model training can take days, making serial iteration prohibitively slow and requiring parallel exploration across multiple research directions; and (2) system complexity, where large configurations, fragile infrastructure dependencies, and multi-day GPU jobs require robust and recoverable execution. We present Auto-RecSys, an autonomous research system for long-horizon experimentation on industry-scale recommendation models. Auto-RecSys addresses these challenges through three harness designs: (1) distributed asynchronous execution for running multiple experiments in parallel across servers, (2) centralized cross-server memory for persistent and recoverable execution across sessions and failures, and (3) cognitive-procedural separation, where natural-language skill files guide LLM reasoning while deterministic scripts enforce operational correctness. Auto-RecSys further employs a dual-loop self-evolving architecture: an Execution Evolution Loop in which model-specific playbooks accumulate operational knowledge by recording failed attempts and crystallizing successful pipelines, and an Idea Evolution Loop in which experimental outcomes inform subsequent ideation. Evaluated on recommendation models, Auto-RecSys significantly reduces the human time required per experiment cycle and improves execution reliability as its playbooks mature.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.10922 — 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 2026-10-16T05:23:56.986Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).