Metraipolis › archive › dc_74e25fc36bb3

PatchScout: Thematic Web Data Collection via Information Foraging — arXiv:2611.00169

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00169
License (as archived)
CC0-1.0
Archived
2026-11-03T11:00:34.767Z
SHA-256 of the archived text
7f00eed85345f7b52de8154bd6f3495b5b98376ac3c0829809a01c2994c30fa0
Stable URL of this page
https://metraipolis.com/documento/dc_74e25fc36bb3

How to cite

PatchScout: Thematic Web Data Collection via Information Foraging — arXiv:2611.00169 — arXiv (en), https://arxiv.org/abs/2611.00169 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_74e25fc36bb3 (Metraipolis archive dc_74e25fc36bb3, sha256 7f00eed85345f7b52de8154bd6f3495b5b98376ac3c0829809a01c2994c30fa0)
BibTeX
@misc{dc74e25fc36bb3,
  title = {PatchScout: Thematic Web Data Collection via Information Foraging — arXiv:2611.00169},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00169},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_74e25fc36bb3; sha256 7f00eed85345f7b52de8154bd6f3495b5b98376ac3c0829809a01c2994c30fa0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00169. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Researchers often need web corpora that are not answers to a single query, but reusable collections of documents spanning many decentralized sources. We refer to this problem as thematic web data collection: assembling semantically relevant documents that share a common theme but are scattered across heterogeneous and structurally disconnected regions of the web. Existing approaches, including traversal-based methods and LLM-driven web agents, are limited by local exploration or short-horizon stopping, preventing comprehensive collection. We formulate this task as a long-horizon information foraging problem over query-induced semantic patches, where the central challenge is deciding when to continue local exploitation and when to switch to new regions. We propose PatchScout, a multi-agent framework that instantiates a class of patch-switching policies to balance local exploitation and adaptive patch switching under a fixed budget. Experiments on four live-web topics show that PatchScout substantially improves yield and domain coverage over traversal-based and search-augmented reasoning agent baselines. In an applied social science setting with an incomplete prior collection, PatchScout discovers 102 previously unidentified entities, illustrating its ability to expand existing thematic datasets.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2611.00169 — 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 2026-11-03T10:59:45.683Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).