Metraipolis › archive › dc_febe967a3bae
Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation — arXiv:2610.07105
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07105
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:20:17.943Z
- SHA-256 of the archived text
a7836936a0a2de5e7ece8d18e2dd98b36bb5c1b0717e9694f17a04df428e914d- Stable URL of this page
https://metraipolis.com/documento/dc_febe967a3bae
How to cite
Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation — arXiv:2610.07105 — arXiv (en), https://arxiv.org/abs/2610.07105 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_febe967a3bae (Metraipolis archive dc_febe967a3bae, sha256 a7836936a0a2de5e7ece8d18e2dd98b36bb5c1b0717e9694f17a04df428e914d)
BibTeX
@misc{dcfebe967a3bae,
title = {Beyond Successor Accuracy: State Retention for Recursive Self-Improvement in Recommendation — arXiv:2610.07105},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07105},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_febe967a3bae; sha256 a7836936a0a2de5e7ece8d18e2dd98b36bb5c1b0717e9694f17a04df428e914d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07105. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recommendation recursive self-improvement (Rec-RSI) feeds recommender outputs into subsequent training. Evaluating each round solely through its latest model assumes that the successor consolidates the update, although pre- and post-update models may retain complementary ranking decisions. We term this \emph{distributed progress} and quantify it using cross-generation advantage (CGA), a marginally matched contrast between cross- and within-generation model pairs. A rank-separation statistic, label-free at selection time, predicts which family to retain. Across four datasets and three sequential recommendation encoders, the preferred retention regime varies by architecture: cross-generation pairing benefits GRU4Rec and SASRec, whereas FMLP initially favors within-generation pairing and shifts toward cross-generation pairing after a second update. Rank separation selects the stronger family in 12/12 first-update and 5/6 second-update dataset-encoder settings; on held-out tests, the selected family outperforms the direct successor in 34/36 trajectories. Five transfer mechanisms do not consistently reproduce these gains in one model. These findings establish state retention as a distinct Rec-RSI problem: progress may reside in relations between generations as well as in the latest model. Code is available at \href{ this https URL }{ 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/2610.07105 — 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 2026-10-07T11:15:24.675Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).