Metraipolis › archive › dc_a19b286ea2df

RecRSI: Mechanism-Guided Discovery of Recommendation Algorithms — arXiv:2611.02487

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02487
License (as archived): CC0-1.0
Archived: 2026-11-03T11:07:43.103Z
SHA-256 of the archived text: 4c2477d8dbb08aba7fd6a82c553fe934d65d8dfb67780f2aa6d7ae2320adbdd8
Stable URL of this page: https://metraipolis.com/documento/dc_a19b286ea2df

How to cite

RecRSI: Mechanism-Guided Discovery of Recommendation Algorithms — arXiv:2611.02487 — arXiv (en), https://arxiv.org/abs/2611.02487 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a19b286ea2df (Metraipolis archive dc_a19b286ea2df, sha256 4c2477d8dbb08aba7fd6a82c553fe934d65d8dfb67780f2aa6d7ae2320adbdd8)

BibTeX

@misc{dca19b286ea2df,
  title = {RecRSI: Mechanism-Guided Discovery of Recommendation Algorithms — arXiv:2611.02487},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02487},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a19b286ea2df; sha256 4c2477d8dbb08aba7fd6a82c553fe934d65d8dfb67780f2aa6d7ae2320adbdd8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02487. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Improving recommendation algorithms for the Web requires coordinating interacting design choices and learning from experiments. We present RecRSI, an LLM-based research framework that uses mechanism hypotheses to organize algorithm discovery. Each hypothesis links a proposed mechanism change to a reference design, a rationale, and an expected observation. MechSpace derives implementable primitives and composition rules from the task source; Research Line uses this space and prior evidence to develop and test hypotheses; Mechanism Feedback carries outcomes and their design context into subsequent research. This organization makes each experiment inform which mechanisms to develop, revise, or combine next. Across four initial recommenders and four datasets, RecRSI yields average relative improvements of 8.48% in NDCG@5 and 6.88% in HR@5 over the initial algorithms, and 2.60% and 2.20%, respectively, over the strongest competing result for each setting and metric. Component and process studies link these gains to coordinated mechanism choices and evidence-guided follow-up. Our code is publicly available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.02487 — 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 2026-11-03T10:59:46.103Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).