Metraipolis › archive › dc_f17e24ef207f

Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation — arXiv:2608.15877

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.15877
License (as archived): CC0-1.0
Archived: 2026-10-18T17:29:20.845Z
SHA-256 of the archived text: fbbad8f97d972733a8380d2cba226eb09b7ac035a1b6445a771e3c7f7a826c8e
Stable URL of this page: https://metraipolis.com/documento/dc_f17e24ef207f

How to cite

Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation — arXiv:2608.15877 — arXiv (en), https://arxiv.org/abs/2608.15877 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f17e24ef207f (Metraipolis archive dc_f17e24ef207f, sha256 fbbad8f97d972733a8380d2cba226eb09b7ac035a1b6445a771e3c7f7a826c8e)

BibTeX

@misc{dcf17e24ef207f,
  title = {Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and Recommendation — arXiv:2608.15877},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15877},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f17e24ef207f; sha256 fbbad8f97d972733a8380d2cba226eb09b7ac035a1b6445a771e3c7f7a826c8e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15877. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Search and recommendation serve a shared discovery objective but encode intent differently. We study this boundary through Dear Algo on Threads, a deployed product where open-ended requests such as \emph{more NBA news} or \emph{less politics} steer subsequent feed recommendations rather than return a one-shot result list. Its agentic intent layer compiles explicit, inferred, negative, and compound intent into a grounded executable plan, then invokes conventional retrieval and optional semantic or multimodal reranking. The layer shares an intent-to-retrieval contract without requiring one model or serving path across search-like and recommendation-like modes. We evaluate Dear Algo under a precision-first objective. In a blinded audit of 300 public request-item pairs (296 evaluable), a strict categorical LLM-as-a-judge gate achieved 94.4\% exact-Relevant precision [88.8\%, 98.9\%]. Across 72 normalized request clusters, the full configuration produced 7.73 judge-qualified candidates per 20 slots versus 6.61 for an LLM-derived-query baseline, a gain of 1.11 [0.12, 2.12]. In a candidate-randomized serving-path study restricted to the reranker path's first 72 eligible hours, the user-weighted judge-Irrelevant share among judged admissions was 2.80\% versus 4.78\% off (-1.97 points [-3.02, -0.94]), while Exact-Relevant share was 2.24 points higher [0.08, 4.41]. Together, these studies show how explicit natural-language intent can be carried into feed recommendation under a precision-first evaluation framework

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15877 — 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 2026-10-18T16:29:13.837Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).