Metraipolis › archive › dc_4650bce84dfa

RecEvolve: A Knowledge-Driven Autonomous Agent System for Recommender Systems — arXiv:2609.01622

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.01622
License (as archived): CC0-1.0
Archived: 2026-10-17T03:26:45.330Z
SHA-256 of the archived text: 40b34d220efbf99c935c69619ac8cdde150cf4c777b0452ec743d77c358541d9
Stable URL of this page: https://metraipolis.com/documento/dc_4650bce84dfa

How to cite

RecEvolve: A Knowledge-Driven Autonomous Agent System for Recommender Systems — arXiv:2609.01622 — arXiv (en), https://arxiv.org/abs/2609.01622 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4650bce84dfa (Metraipolis archive dc_4650bce84dfa, sha256 40b34d220efbf99c935c69619ac8cdde150cf4c777b0452ec743d77c358541d9)

BibTeX

@misc{dc4650bce84dfa,
  title = {RecEvolve: A Knowledge-Driven Autonomous Agent System for Recommender Systems — arXiv:2609.01622},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01622},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4650bce84dfa; sha256 40b34d220efbf99c935c69619ac8cdde150cf4c777b0452ec743d77c358541d9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01622. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The rise of agentic AI has catalyzed a shift toward self-iterating systems, opening new frontiers for the autonomous optimization of production recommender models. This paper presents the empirical validation of a knowledge-driven autonomous agent system, deployed directly on a production large-scale Two-Tower retrieval model. By delegating the entire research lifecycle, spanning idea generation, code implementation, offline training, and metric evaluation, to a continuous closed-loop autonomous framework, the agent system executed over 40 completed autonomous training runs from scratch. Executing these runs under rigorous production-scale evaluations, the system systematically navigated hidden architectural bottlenecks on the latest production model to achieve a breakthrough ~20% relative improvement in NDCG, a gain that translated directly to a +3.77% increase in user satisfaction in live production traffic. Furthermore, the deployment exposed critical vulnerabilities in standard evaluation protocols, as the agent system autonomously discovered reward-hacking shortcuts. These findings prove that an autonomous pipeline can dramatically accelerate the pace of machine learning research and stress-test the rigorousness of underlying experimental infrastructure, while also exposing novel challenges such as reward hacking and redundant exploration of failed hypotheses.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AI).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.01622 — 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 2026-10-17T03:13:12.461Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).